Search

The use of agricultural tractors is a major concern in agriculture safety due to the high level of risk of loss of stability combined with the frequent absence of passive safety devices such as rollover protective structures (ROPSs). Indeed, although in most cases the ROPS is installed, when working in vineyards, orchards, or in other cases of limited crop height, the tractor is usually equipped with a foldable ROPS (FROPS), which is often misused because the effort needed for raising/lowering is excessive and the locking procedure is time-consuming. Thus, the goal of this research is to investigate the problem from the ergonomics point of view, developing a support system capable of facilitating FROPS operations. The research outcome consists of the development of a retrofitted full assistance system (FAS) for lowering/raising the FROPS by means of electric actuators. Additionally, an automatic locking device (ALD) was also developed to safely and automatically lock the FROPS. Both the FAS and ALD systems were implemented following a reverse-engineering approach, while their final validation was performed by means of a real prototype tested in a laboratory. The results achieved can contribute to expanding knowledge on human-centered research to improve safety in agriculture and thus social issues of sustainable agricultural systems.

Reverse engineering (RE) aims to design a new replacement part based on the existing part. The goal is to perform a quality reproduction of the physical part with the best possible mechanical characteristics aiming to find optimal solutions regarding the shape and dimensions of the part. The procedure is implemented through a series of steps: creating a digital 3D model, improving model parameters, and realizing products using additive technologies. In this paper, a review and implementation of the funda– mental methodologies of RE were carried out on the example of a damaged protective cover with an unknown geometry and material essential for the function of a discontinued device with no technical documentation and spare parts. An optical scanning method, 3D CAD, FEA, and additive manufacturing were used to realize the reproduced part. It was shown that by utilizing RE the lifecycle of the device could be significantly extended with minimal cost. Реверзбилни инжењеринг (РЕ) има за циљ да пројектује нови заменски део на основу постојећег дела. Поступак се спроводи кроз низ корака: израда дигиталног 3Д модела, побољшање и оптимизација параметара модела и реализација производа применом адитивних технологија. Циљ је да се изврши квалитетна репродукција физичког дела са најбољим могућим механичким карактеристикама у циљу проналажења оптималних решења у погледу облика и димензија дела. У овом раду је извршен преглед и имплементација основних методологија РЕ на примеру оштећеног заштитног поклопца непознате геометрије и материјала од суштинског значаја за функционисање уређаја који се не производи, а при томе нема расположиве техничке документације и резервних делова. У реализацији репродукованог дела коришћена је метода оптичког скенирања, 3D CAD, FEA и адитивна производња. Показало се да се коришћењем РE може значајно продужити животни циклус уређаја уз минималне трошкове.

Hardware Malware Detectors (HMDs) have recently been proposed to make systems more malware-resistant. HMDs use hardware features to detect malware as a computational anomaly. Several aspects of the detector construction have been explored, leading to detectors with high accuracy. In this paper, we explore whether malware developers can modify malware to avoid HMDs detection. We show that existing HMDs can be effectively reverse-engineered and subsequently evaded. Next, we explore whether retraining using evasive malware would help and show that retraining is limited. To address these limitations, we propose a new type of Resilient HMDs (RHMDs) that stochastically switch between different detectors. These detectors can be shown to be provably more difficult to reverse engineer based on recent results in probably approximately correct (PAC) learnability theory. We show that indeed such detectors are resilient to both reverse engineering and evasion, and that the resilience increases with the number and diversity of the individual detectors. Furthermore, we show that an optimal switching strategy between the RHMDs base detectors not only reduces misclassification on evasive malware but also maintains high classification accuracy on non-evasive malware. Our results demonstrate that these HMDs offer effective defense against evasive malware at low additional complexity

Internet of Vehicles (IoV) has been sought as a solution to realize an Intelligent Transportation System (ITS) for efficient traffic management. Data driven ITS requires learning from vehicular data and provide vehicles with timely information to support a wide range of safety and infotainment ITS applications. IoV is vulnerable to multitude of cyber-attacks and privacy concerns. Feder-ated Learning (FL) is on the verge of delivering the collab-orative learning by exchanging learning model parameters instead of actual data which is expected to provide privacy in IoV. However, despite featuring an inherently secure and privacy-preserving framework, FL is still vulnerable to poisoning and reverse engineering attacks. Blockchain technology (BC) has already demonstrated a zero-trust, fully secure, distributed, and auditable information recording and sharing paradigm. In this paper, we present a practical prospect of blockchain empowered federated learning to realize fully secure, privacy preserving and verifiable FL for the IoV that is capable of providing secure and trustworthy ITS services.

Much software, whether beneficent or malevolent, is distributed only as binaries, sans source code. Absent source code, understanding binaries' behavior can be quite challenging, especially when compiled under higher levels of compiler optimization. These optimizations can transform comprehensible, ``natural" source constructions into something entirely unrecognizable. Reverse engineering binaries, especially those suspected of being malevolent or guilty of intellectual property theft, are important and time-consuming tasks. There is a great deal of interest in tools to ``decompile" binaries back into more natural source code to aid reverse engineering. Decompilation involves several desirable steps, including recreating source-language constructions, variable names, and perhaps even comments. One central step in creating binaries is optimizing function calls, using steps such as inlining. Recovering these (possibly inlined) function calls from optimized binaries is an essential task that most state-of-the-art decompiler tools try to do but do not perform very well. In this paper, we evaluate a supervised learning approach to the problem of recovering optimized function calls. We leverage open-source software and develop an automated labeling scheme to generate a reasonably large dataset of binaries labeled with actual function usages. We augment this large but limited labeled dataset with a pre-training step, which learns the decompiled code statistics from a much larger unlabeled dataset. Thus augmented, our learned labeling model can be combined with an existing decompilation tool, Ghidra, to achieve substantially improved performance in function call recovery, especially at higher levels of optimization.

Mathematical Internet memes are examples of how the creative thrust characterising the Web 2.0 environment reaches the field of mathematics, translating mathematical statements into a new digital form endowed with an epistemic potential that is capable of initiating a process of mathematical argumentation. The research presented in this paper aims to shed light on the creative process of mathematical memes, contributing to building a body of knowledge on mathematical memes that, prospectively, could enable educators to profit from these objects in their teaching. Theoretically, this is based on a widened concept of creativity that focuses on the connection linking digital culture with mathematics, and on distinguishing and merging three perspectives to disclose the meanings of mathematical memes. Methodologically, the process of mathematical memes’ creation is investigated through a reverse engineering approach on a dataset of about 2100 items collected in a 3-year-long ethnographic observation within online communities. The result is a heuristic action model of the creation process, that is validated by creating two new mathematical Internet memes that are shared online within the observed communities to explore if they retain the mathematical and epistemic characteristics of Web-found ones.

This work introduces a generic, machine learning (ML)-based platform for functional reverse engineering (RE) of circuits. Our proposed platform GNN-RE leverages the notion of graph neural networks (GNNs) to (i) represent and analyze flattened/ unstructured gate-level netlists, (ii) automatically identify the boundaries between the modules or sub-circuits implemented in such netlists and (iii) classify the sub-circuits based on their functionalities. For GNNs in general, each graph node is tailored to learn about its own features and its neighboring nodes, which is a powerful approach for the detection of any kind of sub-graphs of interest. For GNN-RE, in particular, each node represents a gate and is initialized with a feature vector that reflects on the functional and structural properties of its neighboring gates. GNN-RE also learns the global structure of the circuit, which facilitates identifying the boundaries between subcircuits in a flattened netlist. Initially, to provide high-quality data for training of GNN-RE, we deploy a comprehensive dataset of foundational designs/components with differing functionalities, implementation styles, bit-widths, and interconnections. GNN-RE is then tested on the unseen shares of this custom dataset, as well as the EPFL benchmarks, the ISCAS-85 benchmarks, and the 74X series benchmarks. GNN-RE achieves an average accuracy of 98:82% in terms of mapping individual gates to modules, all without any manual intervention or post-processing. We also release our code and source data 1.

Disassembly is the basis of static analysis of binary code and is used in malicious code detection, vulnerability mining, software optimization, etc. Disassembly of arbitrary suspicious code blocks (e.g., for suspicious traffic packets intercepted by the network) is a difficult task. Traditional disassembly methods require manual specification of the starting address and cannot automate the disassembly of arbitrary code blocks. In this paper, we propose a disassembly method based on code extension selection network by combining traditional linear sweep and recursive traversal methods. First, each byte of a code block is used as the disassembly start address, and all disassembly results (control flow graphs) are combined into a single flow graph. Then a graph attention network is trained to pick the correct subgraph (control flow graph) as the final result. In the experiment, the compiler-generated executable file, as well as the executable file generated by hand-written assembly code, the data file and the byte sequence intercepted by the code segment were tested, and the disassembly accuracy was 93%, which can effectively distinguish the code from the data.

Obfuscation is a prevalent security technique which transforms syntactic representation of a program to a complicated form, but still keeps program semantics unchanged. So far, developers heavily rely on obfuscation to harden their products and reduce the risk of adversarial reverse engineering. However, despite its spectacular progress, one crucial hurdle is that each of existing obfuscation method is designed specifically for obfuscating one program feature (e.g., identifier name, control flow), so an effective obfuscation scheme usually composes a considerable amount of different obfuscation methods. Therefore, one primary challenge lies in identifying effective combinations of obfuscation methods. In this research, we propose a principled technique for generating an optimal program obfuscation scheme by adopting a reinforcement learning approach. Given a program and a set of obfuscation transformations, a reinforcement learning model is progressively trained to select a sequence of obfuscation transformations, such that applying each transformation in order towards the program yields the optimal obfuscation result, making programs dissimilar while retaining reasonable instrumentation overhead. Our implementation can directly work on raw binary executables without source code, and our evaluation demonstrates that the trained models can effectively obfuscate executable files with low cost.

Formal verification of integer multipliers is one of the important but challenging problems in the verification community. Recently, the methods based on Symbolic Computer Algebra (SCA) have shown very good results in comparison to all other existing proof techniques. However, when it comes to verification of huge and structurally complex multipliers they completely fail as an explosion happens in the number of monomials. The reason for this explosion is the generation of redundant monomials known as vanishing monomials. This paper introduces the SCA-based approach that combines reverse engineering and local vanishing removal to verify large and non-trivial multipliers. For our approach, we first come up with a theory for the origin of vanishing monomials, i.e. we prove that the gates/nodes where both outputs of Half Adders (HAs) converge are the origins of vanishing monomials. Then, we propose a dedicated reverse engineering technique to identify atomic blocks including HAs. The identified HAs are the basis for detecting converging cones and locally removing vanishing monomials which finally results in a vanishing-free global backward rewriting. The efficiency of is demonstrated using an extensive set of multipliers with up to several million gates.

International audience; Identifcation and ftting is an important task in reverse engineering and virtual/augmented reality. Compared to the traditional approaches, carrying out such tasks with a deep learning-based method have much room to exploit. This paper presents SMA-Net (Spatial Merge Attention Network), a novel deep learning-based end-to-end bottom-up architecture, specifcally focused on fast identifcation and ftting of CAD models from point clouds. The network is composed of three parts whose strengths are clearly highlighted: voxel-based multi-resolution feature extractor, spatial merge attention mechanism and multi-task head. It is trained with both virtually-generated point clouds and as-scanned ones created from multiple instances of CAD models, themselves obtained with randomly generated parameter values. Using this data generation pipeline, the proposed approach is validated on two diferent data sets that have been made publicly available: robot data set for Industry 4.0 applications, and furniture data set for virtual/augmented reality. Experiments show that this reconstruction strategy achieves compelling and accurate results in a very high speed, and that it is very robust on real data obtained for instance by laser scanner and Kinect.

Malicious alteration in an IC design is generally referred to as Hardware Trojans (HT). The involvement of multiple entities in the VLSI design cycle has made the process of HT detection very challenging. This paper presents a novel method for the detection of HT at the gate level of abstraction. A path retrace algorithm detects the nets added/deleted by an adversary along with its location. The netlists of the genuine circuit (design netlist) and the Trojan inserted circuit are used by the algorithm to detect the malicious nets in the circuit. This method utilizes testability analysis as the metric for segregating malicious nets in the compromised circuit netlist. Netlist of the fabricated IC, which is obtained through reverse engineering and the design netlist of the original circuit are used to determine the testability parameters such as controllability and observability of the nets. Based on the variation in testability metrics of a signal in the original circuit, the path retrace algorithm identifies the malicious gates inserted into the original circuit. In addition, the algorithm also helps to isolate the Trojan circuit and comprehend its functional implication on the original design. Using the list of malicious gates and compromised circuit netlist, it is possible to identify the Trojan nets inserted by the adversary. This technique is more effective in detecting functional Trojans as compared to techniques employing reverse engineered images as it is design parameter independent and impervious to noise.

The security of hardware intellectual properties (IPs) has become a significant concern, as the opportunity for piracy, reverse engineering, and malicious modification is increasing. Hardware obfuscation has been studied as a potent method to protect against all these attack vectors. However, most of the existing obfuscation techniques have been successfully compromised, where many inherent functional or structural vulnerabilities in these techniques are utilized to reveal the obfuscation key or retrieve the original design. In this paper, we introduce LeGO, a learning-guided obfuscation framework that overcomes known vulnerabilities in a scalable and systematic manner, leading to a robust and lightweight locking mechanism. The proposed framework is guided by our security evaluation process that performs a thorough assessment of an obfuscated IP against various attacks and identifies the vulnerabilities. It then judiciously selects and applies a set of design modification steps or rules that can eliminate these vulnerabilities. Such a rule-based obfuscation process has the distinctive capability to address all existing as well as emerging attacks through the learning of appropriate design transformation steps that prevent these attacks. We present an efficient strategy to apply these rules on a design, while resolving any conflict. Our evaluation of the LeGO framework on a set of ISCAS85 and open-source IP benchmarks has shown promising results in terms of robustness against diverse attacks with an average of area, power and delay overhead of 39%, 45%, and 15%, respectively.

Automated Game Design (AGD) empowers game designers with languages and tools that automate game design processes. Domain- Specific Languages (DSLs) promise to deliver an expressive means for rapidly prototyping and fine-tuning interaction mechanisms that support rich emergent player experiences. However, despite the growing number of studies that center around languages for games and play, few prototypes are ever thoroughly validated and evaluated in practice. As a result, it is not yet well understood what the costs, benefits and limitations of DSL formalisms are. To find out, we investigate to what extent rules, affordances and play can be related by means of source code analysis. We study PuzzleScript, a language and online game engine with an active user community. We reverse engineer PuzzleScript’s design and propose ScriptButler, a novel tool prototype and engine for its analysis. To validate our approach, we conduct an empirical study on the quality of the source code by performing an analysis on a curated collection of 95 games. Our results show that ScriptButler can identify bugs and helps relate PuzzleScript rules to game qualities.

App developers are increasingly using packing services (or packers) to protect their code against being reverse engineered or modified. However, such packing techniques are also leveraged by the malicious developers to prevent the malware from being analyzed and detected by the static malware analysis and detection systems. Though there are already studies on unpacking packed Android apps, they usually leverage the manual reverse engineered packing behaviors to unpack apps packed by the specific packers and cannot be applied to the evolving and new packers. In this paper, we propose a novel unpacking approach with the capacity of adaptively unpacking the evolving and newly encountered packers. Also, we develop a new system, named PackerGrind, based on this adaptive approach for unpacking Android packers. The evaluation with real packed apps demonstrates that PackerGrind can successfully reveal packers? protection mechanisms, effectively handle their evolution and recover Dex files with low overhead.

In this work, we advance the security promise of split manufacturing through judicious handling of interconnects. First, we study the cost-security trade-offs underlying for split manufacturing, which are limiting its adoption. Next, aiming to resolve these concerns, we propose three effective and efficient strategies to dedicatedly lift nets to higher metal layers. Towards this end, we design custom “elevating cells” and devise procedures for routing blockages. All our techniques are employed in a commercial-grade computer-aided design (CAD) framework. For our security analysis, we leverage various state-of-the-art attacks (network flow-based attack, routing-congestion-aware attack, and deep learning-based attack), established metrics (CCR, OER, and HD), and advanced metrics (percentage of netlist recovery and mutual information). Our extensive experiments show that our scheme provides superior protection. Simultaneously, we induce reasonably low and controllable overheads on power and performance, without any silicon area costs. Besides, we support higher split layers, which helps to alleviate concerns on the practicality of split manufacturing.

Our previous work selected for Top Picks in Hardware and Embedded Security 2020 demonstrates that it is possible to reverse engineer neural networks by using side-channel attacks. We developed a framework that considers each part of the neural network separately and then, by combining the information, manages to reverse engineer all relevant hyper-parameters and parameters. Our work is a proof of concept (but also a realistic demonstration) that such attacks are possible and warns that more effort should be given to developing countermeasures. While we have used microcontrollers for our experiments, the attack applies to other targets like FPGAs and GPUs. National Research Foundation (NRF) Accepted version This research is partly supported by the National Research Foundation, Singapore, under its National Cybersecurity Research & Development Programme / Cyber-Hardware Forensic & Assurance Evaluation R&D Programme (Award: NRF2018NCR-NCR009-0001)

The widespread utilization of network protocols raises many security and privacy concerns. To address them, protocol reverse-engineering (PRE) has been broadly applied in diverse domains, such as network management, security validation, and software analysis, by mining protocol specifications. This paper surveys the existing PRE methods and tools, which are based on network trace (NetT) or execution trace (ExeT), according to features representation. The feature-based protocol classification is proposed for the first time in literature to describe and compare different tools more clearly from a new perspective and to inspire crossover approaches in future works. We analyze the rationale, genealogy, contributions, and properties of 74 representative PRE methods/tools developed since 2004. In addition, we extend the general process of the PRE from a feature perspective and provide a detailed evaluation of the well-known methods/tools. Finally, we highlight the open issues and future research directions.

The aim of this work is to develop a methodology for Pelton turbines performance improvement using reverse engineering, parametric design and CFD analysis. The methodology was applied on a real turbine from the company ELEPCO S.A. Initial geometry was obtained using resin and plaster mold, 3D scanning was applied to acquire a point cloud. The parametric CAD model was obtained by using Python along with parametric design tools from Autodesk Inventor. The optimization of the model was achieved by varying the entry and exit angles of the bucket. Numerical simulation was executed using ANSYS CFX with k-ω SST turbulence model.

Surface morphology of the components is a key factor that influences the quality and performance of precision systems. The influence of different morphologies on the contact performance of mating surfaces may be studied by simulating a real rough surface and calculating the contact performance. First, the micro-geometric characteristics of the surfaces of the machined parts are measured by a 3D surface profilometer (NV5000 5022S), and the distribution law of the surface micro-geometric characteristics is obtained by statistical and characterization methods. Second, the rough surface conforming to this law is simulated by a non-Gaussian mathematical algorithm, and the contact model between the mating parts with micro-geometric characteristics of the simulated surface is reconstructed using reverse engineering. Finally, the mechanical properties of the mating surfaces are obtained using a numerical algorithm based on Yoshimura's integral method and tests. The comparison of mechanical properties obtained from numerical analysis and test shows that the maximum errors in the contact stiffness obtained by the two methods are 9.4% (grinding surface) and 11.5% (milling surface), respectively. Therefore, it is feasible to use a non-Gaussian simulation method and Yoshimura's integral method to realize an effective simulation of the micro-geometric characteristics of the surface and the analysis of the contact performance of the mating surface respectively. The results obtained from this study is thus important as a reference for the analysis of the surface morphology and mechanical properties between the matching parts.

Quick, early, and precise detection is important for diagnosis to control the spread of COVID-19 infection. Artificial Intelligence (AI) technology could certainly be used as a modulating tool to ease the detection, and help with the preventive steps further. Convolutional neural networks (CNNs) have achieved state-of-the-art performance in many visual recognition tasks. Nevertheless, most of these state-of-the-art networks highly rely on the availability of a high amount of labeled data, being an essential step in supervised machine learning tasks. Conventionally, this manual, mundane, and time-consuming process of annotating images is done by humans. Learning to localize or detect COVID-19 infection masks in our specific case study typically requires the collection of CT scan data that has been labeled with bounding boxes or similar annotations, which generally is limited. A technique that could perform such learning with much less annotations, and transfer the learned proposals that are algorithm-driven to generate more synthetic annotated samples would be helpful & quite valuable. We present such a technique inspired by weakly trained mask region based convolutional neural networks (R-CNN) architecture for localization, in which the number of images with their pixel-level masks can be a small proportion of the total dataset, and then further improvise CNNs by inversely generating dense annotations on-the-go using an algorithmic-based computational approach. We focus on alleviating the bottleneck associated with deep learning models needing annotated data for training in an intuitive reverse engineering fashion through this work. Our proposed solution can certainly provide the prospect of automated labeling on-the-fly, thereby reducing much of the manual work. As a result, one can quickly train a precise COVID-19 infection detector with the leverage of autonomous frame-by-frame machine generated annotations. The model achieved mean precision accuracy (%) of 0.99, 0.931, and 0.8 for train, validation, and test set, respectively. The results demonstrate that the proposed method can be adopted in a clinical setting for assisting radiologists, and also our fully autonomous approach can be generalized to any detection/recognition tasks at ease.

The mobile malware is scaling up in terms of numbers and in degree of sophistication. The analysis of mobile malware is challenging for several reasons e.g., mobile apps are context aware and use the device resources which can pose greater risks for their security. In this work, a novel approach for the analysis of mobile malware is explored. The mobile malware is analyzed buying the commercially available reverse engineering tools. The complete cycle of reverse engineering is narrated for a benchmark mobile malware which starts from apk file to java code. The reverse engineered code of malware is of huge importance for extracting the malware patterns especially from sophisticated malwares like spyware and Trojans. The results show that the tools can be used to extract the complete source code of the malware which can potentially be used for dynamic analysis.

The smart city landscape is rife with opportunities for mobility and economic optimization, but also presents many security concerns spanning the range of components and systems in the smart ecosystem. One key enabler for this ecosystem is smart transportation and transit, which is foundationally built upon connected vehicles. Ensuring vehicular security, while necessary to guarantee passenger and pedestrian safety, is itself challenging due to the broad attack surfaces of modern automotive systems. A single car contains dozens to hundreds of small embedded computing devices known as electronic control units (ECUs) executing 100s of millions of lines of code; the inherent complexity of this tightly-integrated cyber-physical system (CPS) is one of the key problems that frustrate effective security. We describe an approach to help reduce the complexity of security analyses by leveraging unsupervised machine learning to learn clusters of messages passed between ECUs that correlate with changes in the CPS state of a vehicle as it moves throughout the world. Our approach can help to improve the security of vehicles in a smart city, and can leverage smart city infrastructure to further enrich and refine the quality of the machine learning output.

Decompilers are indispensable tools in Android malware analysis and app security auditing. Numerous academic works also employ an Android decompiler as the first step in a program analysis pipeline. In such settings, decompilation is frequently regarded as a "solved" problem, in that it is simply expected that source code can be accurately recovered from an app. On the other hand, it is known that, e.g, obfuscation can negatively impact a decompilers effectiveness. Therefore, in order to better understand potential failure modes of, e.g., automated analysis pipelines involving decompilation, it is important to characterize the performance of decompilers on both benign and malicious apps. To this end, we have performed what is, to the best of our knowledge, the first large-scale study of Android decompilation failure rates, using three sets of apps; namely, 3,018 open-source apps, 13,601 apps crawled from Google Play, and an existing collection of 24,553 malware samples. In addition to the state-of-the-art Dalvik bytecode decompiler Jadx, we also studied the performance of three popular Java decompilers. Furthermore, this paper also presents the findings from a follow-up study on 54,945 malware apps, where we additionally performed an analysis of the reasons for decompilation failures. Our study revealed that decompilers generally have very low failure rates, and that few failures on benign apps appear to be related to obfuscation. On malware, however, obfuscation appears to be a more prominent cause of failures, although the vast majority of malicious apps could still be fully decompiled by an ensemble of decompilers. Funding Agencies|Swedish Graduate School in Computer Science (CUGS); Excellence Center at Linkoeping - Lund in Information Technology (ELLIIT)

With ever-increasing, internet-connected devices provide an opportunity to fulfil the attacker’s malicious intention. They use malicious programs to compromise the devices and use them to infect others also. The security researchers are straggling to develop a technique that detects all the malware accurately because of the use of invincible techniques in the development of malware such as strong encryption, obfuscation, polymorphic and metamorphic engine. In this context, this paper proposes a novel malware classification with fine-tune convolution neural networks (MCFT-CNN) model. The MCFT-CNN model detects the unknown malware sample without feature engineering and prior knowledge of binary code analysis or reverse engineering, even the advanced evading techniques used to develop the malware. The model uses deep transfer learning to classify the malware images to their respective malware families. The proposed model enhances the ResNet50 model by altering the last layer with a fully connected dense layer. The output of fully connected dense layer and knowledge of ImageNet model are supplied to softmax layer for malware classification. The model is trained with MalImg malware datasets. The proposed model reported 99.18% accuracy and 5.14ms prediction time. The model also shows consistent performance with a relatively larger dataset (Microsoft malware challenge dataset, approximately 500GB) with 98.63% accuracy and 5.15ms prediction time. The proposed model shows consistent efficacy with two benchmark datasets that clarify the model’s generalisability to perform on the diverse datasets.

3D optical scanning method, is employed to digital shape and geometric dimension analysis of fuel tanks. The following paper presents the application possibilities of the optical 3D measurement method for measuring and archiving dimensions of geometrically complex parts, on the example of a passenger car fuel tank in local company. Based on the conducted measurements, for a specific type and size of the population of fuel tanks, proposed model that classifies the geometric accuracy of the tanks produced in the production line. For the analysis and data processing different informatics techniques have been used. The main objective of theirs was to identify the possibility of implementing the system for automation of the measurement to the production line. The measurements were implementation at local company - a manufacturer of polymer tanks in the automotive industry. For most of the measuring points, the mean value of the measuring deviations ranged from -1 mm to +1 mm. The mean values of the standard deviations are presented for a representative deviation of the X dimension of 0.1; 5; 10; 15 and 20 mm were respectively: 0.014; 0.150; 0.172; 0.289; 0.340 mm. The dimensional shape assessment of the manufactured tanks is extremely important from the point of view of the automation of this task in the production line. The optimization of the measurement of tanks carried out in laboratory conditions was implemented on the production line. The main task of optical scanning for the assessment of dimensional conformity has not been used so far in factory. This is due not only to the cost of such systems, but also to certain limitations that have been resolved thanks to laboratory tests. The obtained results of the metrological inspection make it possible to identify significant dimensional and shape deviations of automatically manufactured tanks. The proposed use of artificial neural networks allows the production with a high quality of tanks accuracy with the minimum the number of scanned tanks in the production line. The paper also presents the possibilities of the computer software to analyze the deviations of geometrically very complex parts.

Purpose: Malicious software or malware is a real threat to the security of computer systems or networks. Researchers made various attempts to find information and knowledge about malware, including preventing or even eliminating it. One effort to detect it is using a malware dynamic analysis model based on reverse engineering techniques. However, there are many reverse engineering techniques proposed with various stages and requirements in the literature. Methods: This research uses an experimental method. The object of research is a malware analysis model using reverse engineering techniques. The experimental method used is qualitative, collecting data related to the advantages and disadvantages of the reverse engineering-based malware analysis models used as a reference in this study. The data is used as consideration to propose a new model of malware analysis utilizing reverse engineering techniques. Result: In this study an analysis model of malware was proposed by synthesizing several reverse engineering-based malware analysis models. Novelty: The proposed model was then tested in a virtual environment where it is proven to be more effective than previous models for analyzing malware.

The objective of this work is to propose an advanced automated damage detection and damage reconstruction algorithm for damaged gear tooth repair. It can automate tool path design and provide precise repair volume detection for complex repair volume. First, models of the damaged and nominal parts were obtained by reverse engineering. Next, the damaged model was aligned with the nominal model. After that, both models were sliced into layers, and a set of parallel and equidistant casting rays was used to intersect with these layers to extract the repair volume. Then the repair tool path was generated and used to guide the laser additive manufacturing process for repair. The corresponding repair experiment and validated numerical model based on repairing a complex gear fracture was conducted to evaluate the reconstruction algorithm efficiency and repair part quality. Microstructure analysis and Vickers hardness test were carried out to evaluate the repaired part quality. The coincidence of scanning points between repaired model and the nominal model is high. The repair experiment confirmed the strong efficiency of this repair algorithm for complex geometry repair. A 3D finite element model was also developed to simulate the repair process and provide critical deformation and residual stress of the repaired parts. The predicted temperature and residual stress results were compared and showed a good agreement with the experimental measurements. These results further validated that the proposed repair algorithm and simulation model are suitable and efficient for the automated repair of damaged components.

According to recent reports and surveys over the last 2 years, field-programmable gate arrays (FPGAs) have increasingly become the prime targets for carrying out extremely sophisticated cyber-attacks. FPGAs incorporate runtime reconfiguration capabilities, which allow modular designs to be mapped. Low-end FPGAs are widely used in many networking applications where severe cost, power, and resource constraints persist. These constraints force a tradeoff for FPGA developers regarding FPGA security features such as encryption of FPGA bitstreams. As a result, critical security issues arise, such as hardware Trojan (HT) insertion. Attackers can attempt to gain control of the FPGA during run-time for Trojan insertion by bitstream reverse engineering. In this paper, we turn the tables and provide a proof of concept for an approach that utilizes bitstream reverse engineering for Trojan detection. Our approach is bottom-up: it starts with bitstream inspection, FPGA component identification from the layout, and follows up with identification of malicious configurations. Due to this bottom-up approach, any stealthy malicious circuit can be detected, which is difficult to achieve through conventional design analysis methods. We leverage open-source tools, publicly available datasets and vendor provided tools. The method is generic and can be applied to a wide range of FPGAs. An example of Trojan detection is shown for Xilinx Virtex5 VLX50T FPGA. Once a reference database is created, the Trojan detection is very fast and takes less than a minute on a general-purpose Intel Core i5 processor-based computer. The proposed Trojan detection approach is, to the best of our knowledge during publication, the only open source, software-based, low-cost alternative to time consuming design re-construction and analysis based approaches. It can be applied at the customer end without requiring any hardware alteration/IP updates from FPGA vendors.

Quantum computing is now a reality, and its incomparable computational power has led companies to show a great interest in being able to work with quantum software in order to support part of their current and future business operations. However, the quantum computing paradigm differs significantly from its classical counterparts, which has brought about the need to revolutionise how the future software is designed, built, and operated in order to work with quantum computers. Since companies cannot discard all their current (and probably mission-critical) information systems, they must adapt their classical information systems to new specific quantum applications, thus evolving towards hybrid information systems. Unfortunately, there are no specific methods with which to deal with this challenge. We believe that reengineering, and more specifically, software modernisation using model-driven engineering principles, could be useful as regard migrating classical systems and existing quantum programs towards hybrid information systems. This paper, therefore, presents QRev, a reverse engineering tool that analyses quantum programs developed in Q# in order to identify its components and interrelationships, and then generates abstract models that can be used in software modernisation processes. The platform-independent models are generated according to the Knowledge Discovery Metamodel (KDM) standard. QRev is validated in a case study involving five quantum programs in order to demonstrate its effectiveness and scalability. The main implication of the study is that QRev can be used in order to attain KDM models, which can subsequently be employed to restructure or add new quantum functionality at a higher abstraction level, i.e. independently of the specific quantum technology.

Fringe projection profilometry (FPP) is a technique used for obtaining the three-dimensional shape of an object in fields such as reverse engineering, cultural heritage, and computer vision. The FPP measurement accuracy significantly depends on the arrangement of the measurement system, measurement space conditions, equipment setting, and object characteristics. However, experimental verification of the measurement conditions is time-consuming and expensive. This study presents a simulator that can set a broader range of measurement conditions. This simulator was developed using Unity, which is an integrated development environment for video games. The proposed simulator can be configured with a graphical user interface for device placement and operation, and it can freely adjust the aperture, exposure time, and depth-of-field of the camera. The measurement simulation results for a CAD model obtained using the proposed simulator are presented. The results indicate that camera defocus or unfit exposure time causes phase measurement errors.

Refuelling is an important activity in the daily routines at airports. Airport oil pits are covered, requiring a special pit-opener to open its lid. After using the pit-opener, there is no designated place to store the pit-opener. Due to the weight of the pit-opener, workers have difficulty in opening, carrying and using the existing pit-opener, which poses risks of musculoskeletal injuries. Often, workers would throw the tool to the ground, causing impact or possible damage. Hence, there is a need for a new pit-opener design to solve this problem, which is lightweight and high-strength. An invention of a new Pit-Opener (DAG) is presented, comprising of a flexible hook at one side and a fixed hook at the adjacent side. In addition, the Pit-Opener (DAG) consists of a handle, stowage bracket and body support. The objective of this paper is to determine the optimal configurations by mass reduction of the DAG prototype. The functionality of DAG has significantly improved the airport worker’s job with regards to ease of use, however, the prototype may still be heavy for long repetitive use. The methodology used in this study consists of using a reverse engineering process to create a CAD model based upon the DAG prototype, conducting stress analysis study and interactive design through a user-centered and systematic design approach. Consequently, the optimization process of the pit-opener design was performed via stress analysis using a Finite-Element Analysis (FEA) tool through iterations with different configurations to obtain the final optimised design. The results permitted an overall further weight reduction of 2 kg of the existing prototype, without sacrificing performance. An evaluation of the model using the Parsimony, Exactness, Precision, Specialization (PEPS) method was used for validation. In conclusion, DAG provides cost-effective, vital, safe and secured storage of efficient pit opening for oil tanker application, and through structural analysis, suitable configurations of the pit-opener were determined.

Autologous ear reconstruction is the preferred treatment in case of partial or total absence of the patient external ear. This kind of surgery can be really challenging since precise replication of complex three-dimensional structure of the ear is crucial to provide the patients with aesthetically consistent reconstructed anatomy. Therefore, the results strongly depends on the “artistic skills” of the surgeon who is in charge to carry out a three-dimensional sculpture, which resembles the shape of a normal ear. In this context, the definition of a preoperative planning and simulation process based on the patient's specific anatomy may help the surgeon in speeding up the ear reconstruction process and, at the same time, to obtain better results, thus allowing a superior surgical outcome. In the present work the main required features for performing an effective simulation of the ear reconstruction are identified and a strategy for their interactive design and customization is devised with the perspective of a semi-automatization of the procedure. In detail, the paper provides a framework which start from the acquisition of 3D data from both a healthy ear of the patient (or, if not available e.g. due to bilateral microtia of the ear of one of his parents or from a template) and of costal cartilage. Acquired 3D data are properly processed to define the anatomical elements of the ear and to find, using nesting-based algorithms, the costal cartilage portions to be used for carving the ear itself. Finally, 3D printing is used to create a mockup of the ear elements and a prototype of the ear to be reconstructed is created. Validated on a test case, the devised procedure demonstrate its effectiveness.

Complex problem solving in applied settings within the realm of IT security is an emergent field of psychological research. We propose an experimental study design on de-camouflaging, a task that is routinely performed during hardware reverse engineering. This task consists of determining the identity of camouflaged gates within Boolean networks that are purposely designed to have an identical appearance despite their different functions. In an experimental study manipulating representation as an experimental factor and investigating expertise as a quasi-experimental factor, we aim to understand whether problem solving is facilitated by a depictive compared to a descriptive representation.

Non-adiabatic holonomic quantum computation is a method used to implement high-speed quantum gates with non-Abelian geometric phases associated with paths in state space. Due to their noise tolerance, these phases can be used to construct error resilient quantum gates. We extend the holonomic dark path qubit scheme in [M.-Z. Ai {\t et al.}, Fundam. Res. {\bf 2}, 661 (2022)] to qudits. Specifically, we demonstrate one- and two-qudit universality by using the dark path technique. Explicit qutrit ($d=3$) gates are demonstrated and the scaling of the number of loops with the dimension $d$ is addressed. This scaling is linear and we show how any diagonal qudit gate can be implemented efficiently in any dimension., New figure 2 added; several minor changes; references added; journal reference added

Image segmentation and segmentation of geometry are one of the basic requirements for reverse engineering, shape synthesis, and shape optimization. In terms of shape optimization and shape synthesis where the original geometry should be faithfully replaced with some mathematical parametric model (NURBS, hierarchical NURBS, T-Spline, …) segmentation of geometry may be done directly on 3D geometry and its corresponding parametric values in the 2D parametric domain. In our approach, we are focused on segmentation of 2D parametric domain as an image instead of 3D geometry. The reason for this lies in our dynamic hierarchical parametric model, which controls the results of various operators from image processing applied to the parametric domain.

Given that many models of design-based learning in science education are grounded in forward engineering, in which students are challenged to use the engineering design process to achieve unknown solutions to engineering problems, this study aims to examine the potential of using reverse engineering, as an alternative approach to design-based learning, to facilitate students’ understanding of scientific concepts. Two classes of ninth-grade students, one with 21 students and the other with 24 students, participated in this study by engaging in reverse engineering activities where they dissected and investigated how a bimetal thermostat functions. The primary instrument is a conceptual test, comprising 12 multiple-choice questions about thermal expansion, which was completed by the students before and after the reverse engineering activities. A paired-samples t-test was used to analyse the data. Discourse analysis of students’ verbal interactions within small groups was also used to illustrate their learning process. The results indicate that both classes exhibited significant improvements in their understanding of thermal expansion, to a large or medium extent. Thus, it is recommended that reverse engineering can be used as a pedagogical approach to facilitating students’ learning of scientific concepts.

Reverse engineering the brain by mimicking the structure and function of neuronal networks on a silicon integrated circuit was the original goal of neuromorphic engineering, but remains a distant prospect. The focus of neuromorphic engineering has thus been relaxed from rigorous brain mimicry to designs inspired by qualitative features of the brain, including event-driven signalling and in-memory information processing. Here we examine current approaches to neuromorphic engineering and provide a vision that returns neuromorphic electronics to its original goal of reverse engineering the brain. The essence of this vision is to ‘copy’ the functional synaptic connectivity map of a mammalian neuronal network using advanced neuroscience tools and then ‘paste’ this map onto a high-density three-dimensional network of solid-state memories. Our copy-and-paste approach could potentially lead to silicon integrated circuits that better approximate computing traits of the brain, including low power, facile learning, adaptation, and even autonomy and cognition. This Perspective explores the potential of an approach to neuromorphic electronics in which the functional synaptic connectivity map of a mammalian neuronal network is copied using a silicon neuro-electronic interface and then pasted onto a high-density three-dimensional network of solid-state memories.

Typically, a coach may follow a process in which they first identify the key performance indicators of their sport, determine the physical attributes that map back to them, and then distribute the development of those capacities over the allocated timeframe. Furthermore, effective training plans are based on a theoretical or biological basis for how we move and adapt to exercise stimuli, coupled with an understanding of how these are best sequenced, such that one stimulus and subsequent adaptation can potentiate the next. Thus, reverse or backward engineering, when appropriately converged with the plans of those devised around nutrition, conditioning, technical, and tactical training for example likely gives athletes the best chance of attaining their performance goals. The aim of this paper is to describe the application of reverse engineering, exampling it within the context of developing an athlete who can demonstrate a high level of agility.

3D scanning devices are traditionally employed in reverse engineering tasks that can be carried out semi-automatically, with user assistance. However, their application in manufacturing process control requires automatic point cloud segmentation and extraction of geometric primitives. In this paper, we propose a method for automatic recognition of planes and cylinders (most frequently encountered geometric primitives in mechanical engineering) from unstructured point clouds. The method is based on the scatter of data during least squares fitting of second order surfaces. It consists of three phases and the first phase represents automatic point cloud segmentation. The second phase deals with merging of over-segmented regions and surfaces parameters estimation, whereas the final phase provides extraction of recognized geometric primitives. The method is experimentally verified using three real-world case studies, and its performances are compared with two state of the art recognition algorithms. The results have shown that the proposed method outperforms alternative approaches in terms of appropriately recognized planes and cylinders without surface type confusion, as well as when the recognition of non-existent primitives is considered. In addition, the method determines surfaces parameters with high accuracy.

One of the key components in making Industry 4.0 a reality includes machines that are able to produce re-quired products and components faster, more precisely and more flexibly than ever before based on so-called reverse engineering technology. Reverse engineering is a technology which enables rapid acquisition of data for CAD, CAM, CAE, thereby greatly shortening the development, design and fabrication of parts. In general, analog data is converted to digital data, which is further processed. The paper deals with the analysis of prototype models of disc milling cutters with different blade profiles. The inspection of the shape of the disc-type prototypes is based on the reading of the digitized reference CAD model ( workpiece with machined grooves), the subsequent positioning of the digitized protrusions of the disc mill cutters (milling cutter with edge profile 1, milling cutter with edge profile 8) with respect to this reference CAD model, creating a colour map of the deviations at the selected points. The aim of the paper was to analyse the resulting wear (deviation of the dimensions at selected points) on the prototype of the disc milling cutters with the profiles of the blades 1 and 8, which was simplified on the workpiece with the machined profiles of the grooves 1 to 4., European Regional Development Fund, ERDF, European Regional Development Fund; project: Advancement and support of R&D for "Centre for diagnostics and quality testing of materials" in the domains of the RIS3 SK specialization [ITMS2014+: 313011W442]

Optically variable devices (OVDs) are in tremendous demand as optical indicators against the increasing threat of counterfeiting. Conventional OVDs are exposed to the danger of fraudulent replication with advances in printing technology and widespread copying methods of security features. Metasurfaces, two-dimensional arrays of subwavelength structures known as meta-atoms, have been nominated as a candidate for a new generation of OVDs as they exhibit exceptional behaviors that can provide a more robust solution for optical anti-counterfeiting. Unlike conventional OVDs, metasurface-driven OVDs (mOVDs) can contain multiple optical responses in a single device, making them difficult to reverse engineered. Well-known examples of mOVDs include ultrahigh-resolution structural color printing, various types of holography, and polarization encoding. In this review, we discuss the new generation of mOVDs. The fundamentals of plasmonic and dielectric metasurfaces are presented to explain how the optical responses of metasurfaces can be manipulated. Then, examples of monofunctional, tunable, and multifunctional mOVDs are discussed. We follow up with a discussion of the fabrication methods needed to realize these mOVDs, classified into prototyping and manufacturing techniques. Finally, we provide an outlook and classification of mOVDs with respect to their capacity and security level. We believe this newly proposed concept of OVDs may bring about a new era of optical anticounterfeit technology leveraging the novel concepts of nano-optics and nanotechnology.

Recently, design thinking has become recognized as a necessity for every student, especially when they engage in design-based learning, as a pedagogical approach to science, technology, engineering, and mathematics education. However, design-based learning is mostly based on forward engineering, in which students’ design thinking can be nurtured by designing unknown solutions. Little is known about whether design thinking can be facilitated in the context of reverse engineering, when students learn from already designed products. This study therefore seeks to explore the perceptions of 38 ninth-grade students on the characteristics of design thinking before and after a four-week reverse engineering project, using Likert scales to measure six aspects of design thinking, namely (a) being comfortable with uncertainty and risks, (b) human-centeredness, (c) mindfulness to the process and impacts on others, (d) collaboratively working with diversity, (e) orientation to learning by making and testing, and (f) being confident and optimistic to use creativity. The data were analyzed using descriptive and inferential statistics, including means, standard deviations, paired-samples t-tests, and Wilcoxon signed-rank tests. The results indicate that two aspects, human-centeredness and being confident and optimistic to use creativity, were significant (p = 0.008 and p = 0.043, respectively), with size effects of 0.43 and 0.34, respectively. Based on this potential, reverse engineering can be a design-based learning approach to facilitate students’ design thinking. It is recommended that instructional activities involving reverse engineering maintain some degree of ambiguity and risk to prevent design fixation among students.

Usage of simulation techniques like Vehicle-in-the-Loop, Scenario-in-the-Loop, and other mixed-reality systems are becoming inevitable in autonomous vehicle development, particularly in testing and validation. These methods rely on using digital twins, realistic representations of real vehicles, and traffic in a carefully rebuilt virtual world. Recreating them precisely in a virtual ecosystem requires many parameters of real vehicles to follow their properties in a simulation. This is especially true for vehicle dynamics, where these parameters have high impact on the simulation results. The paper's objective is to provide a method that can help reverse engineering a real car's suspension characteristics with the help of a genetic algorithm. A detailed description of the method is presented, guiding the reader through the whole process, including the meta-heuristic function's settings and how it interfaces with IPG Carmaker. The paper also presents multiple measurements, which can be effortlessly recreated without expensive devices or the need to disassemble any vehicle parts. Measurements are reproduced in two separate simulation tools with special scenarios providing an efficient way to analyze and verify the results. The provided method creates vehicle suspension characteristics with adequate quality, opening up the possibility to use them in the creation of digital twins or creating virtual traffic with realistic vehicle dynamics for high-quality visualization. Results show satisfying accuracy when tested with OpenCRG.

The paper describes a solution of reverse engineering tasks using the equipment of the laboratory of the Technical University in Zvolen. The first task was linked to evaluation of a wear rate of the tool used to for mulching and elimination of unwanted wood or weed vegetation. The obtained data will be used as a base line for determination of the time interval for the tool replacement. We developed a prototype of components and their drawing documentation for a single-purpose machine for cutting barley. We created the 3D model using the method of photogrammetry. The finished drawing documentation and prototypes were handed over to the company KRUP. Finally, we identified the most suitable procedures for creating a model of a part with a complex shape. We tested the techniques of editing the point cloud processing, as well as of smoothing the surfaces and automating the creation of partial geometric elements of the model. Based on the properties of the component, which is the starting point of the entire reverse engineering process and from the achieved results, we set recommendations for the selection of appropriate procedures.