Search

Summary: The difficulty of obtaining reliable individual identification of animals has limited researcher's ability to obtain quantitative data to address important ecological, behavioral, and conservation questions. Traditional marking methods placed animals at undue risk. Machine learning approaches for identifying species through analysis of animal images has been proved to be successful. But for many questions, there needs a tool to identify not only species but also individuals. Here, we introduce a system developed specifically for automated face detection and individual identification with deep learning methods using both videos and still-framed images that can be reliably used for multiple species. The system was trained and tested with a dataset containing 102,399 images of 1,040 individuals across 41 primate species whose individual identity was known and 6,562 images of 91 individuals across four carnivore species. For primates, the system correctly identified individuals 94.1% of the time and could process 31 facial images per second.

Abstract In general, the space-time adaptive processing (STAP) can achieve excellent clutter suppression and moving target detection performance in the airborne multiple-input multiple-output (MIMO) radar for the increasing system degrees of freedom (DoFs). However, the performance improvement is accompanied by a dramatic increase in computational cost and training sample requirement. As one of the most efficient dimension-reduced STAP methods, the extended factored approach (EFA) transforms the full-dimension STAP problem into several small-scale adaptive processing problems, and therefore alleviates the computational cost and training sample requirement. However, it cannot effectively work in the airborne MIMO radar since sufficient training samples are unavailable. Aiming at the problem, a fast iterative method using persymmetry covariance matrix estimation in the airborne MIMO radar is proposed. In this method, the clutter covariance matrix is estimated by the original data and the constructed data. Then, the spatial weight vector in EFA is decomposed into the Kronecker product of two short-weight vectors. The bi-iterative algorithm is exploited to obtain the desired weight vectors. Simulation results demonstrate the effectiveness of our proposed method.

Application repackaging is a severe problem for Android systems. Many Android malware programs pass the mobile platform fundamental security barriers through repackaging other legitimate apps. Most of the existing anti-repackaging schemes only work at the Android DEX bytecode level, but not for the shared object files consisting of native ARM-based machine instructions. Lacking the protection at the native machine code level opens a door for attackers to launch repackaging attacks on the shared libraries that are commonly used on Android apps. This paper presents CodeCloak, a novel anti-repackaging system to protect Android apps at the native code level. CodeCloak employs binary-level code virtualization techniques to protect the target application. At the native machine code level, it uses a newly designed stack-based virtualization structure to obfuscate and protect critical algorithm implementations that have been compiled into native instructions. It leverages multiple dynamic code protection schemes to increase the diversity of the program behavior at runtime, aiming to increase the difficulties for performing code reverse engineering. We evaluate CodeCloak under typical app repackaging scenarios. Experimental results show that CodeCloak can effectively protect apps against repackaging attacks at the cost of minimum overhead.

To protect programs from unauthorized analysis, virtualize the code based on Virtual Machine (VM) technologies is emerging as a feasible method for accomplishing code obfuscation. However, in some State-of-the-art VM-based protection approaches, the set of virtual instructions and bytecode interpreters are fixed across the whole programs. This means an experienced attacker could extract the mapping information between virtual instructions and native code from programs, and use this knowledge to uncover the mapping relationships in similar protecting applications. To address this problem, we present CoDiver (Code Virtualization Protection with Diversity), a novel VM-based code obfuscation system in this paper. The main idea of our approach is to obfuscate the mapping between the opcodes of bytecode instructions and their semantics. To achieve this goal, we first turn every protected code region into multiple parts by partition proceeding, randomize the mapping of opcodes and their semantics of each part. By this way, we could translate the bytecode instruction into different native code in different sections of the obfuscated code. This method could increase the diversity of program behavior significantly. As a result, it will be useless to learn the mapping relationship between bytecode and native code of some other programs, then migrate it into a new program. We build a prototype of CoDiver and tested it on a set of real-world applications. Experimental results show that as compared with two state-of-the-art VM-based code obfuscation approaches, our approach is more effective and could provide stronger protection with comparable runtime overhead and code size.

Code obfuscation built upon code virtualization technology is one of the viable means for protecting sensitive algorithms and data against code reverse engineering attacks. Code virtualization has been successfully applied to programming languages like C, C++, and Java. However, it remains an outstanding challenge to apply this promising technique to JavaScript, a popular web programming language. This is primarily due to the open visibility of JavaScript code and the expensive runtime overhead associated with code virtualization. This paper presents JSPro, a novel code virtualization system for JavaScript. JSPro is the first JavaScript code obfuscation tool that builds upon the emerging WebAssembly language standard. It is designed to provide more secure code protection but without incurring a significant runtime penalty, explicitly targeting numerical JavaScript kernels. We achieve this by first automatically translating the target JavaScript code into WebAssembly and then performing code obfuscation on the compiled WebAssembly binary. Our design has two advantages over existing solutions: (1) it increases the code reverse entering complexity by implementing code obfuscation at a lower binary level and (2) it significantly reduces the performance impact of code virtualization over the native JavaScript code by using the performance-tuned WebAssembly language. We evaluate JSPro on a set of numerical JavaScript algorithms widely used in many applications. To test the performance, we apply JSPro to four mainstream web browsers running on three distinct mobile devices. Compared to state-of-the-art JavaScript obfuscation tools, JSPro not only provides stronger protection but also reduces the runtime overhead by at least 15% (up to 38.2%) and the code size by 28.2% on average.

Performance of a collaborative task is mostly dependent on the collective effort from participants. To accomplish a participatory task effectively and efficiently, the team formation problem (TFP) outweighs all other considerations. It is even more complicated when social connections among candidates is taken into account. As we can imagine, a large number of tasks require members of the team to be socially close. On the contrary, a portion of tasks, e.g., proposal review, pay more attention to a multidimensional view, and team members should be selected from a variety of cliques. Due to the nature of tasks, it is challenging to find a subset that meets the skill requirement of the task as well as socially diversity demand of team members from a pool of candidates. In this paper, we explore the TFP in a social network. Based on different task objectives, we first formulate the TFP as TFP with strong ties (TFP-ST) and TFP with weak ties (TFP-WT), respectively. Both TFP-ST and TFP-WT are proven to be NP-hard, and we then design corresponding heuristic algorithms to solve the two problems. Through extensive simulations, we show that the solution to TFP-ST can achieve significant improvement in terms of collaboration cost, team size, as well as running time, and the solution to TFP-WT can provide better performance than existing approaches at the same time.

In wireless sensor networks (WSNs), Radio Signal Strength Indicator (RSSI)-based localization techniques have been widely used in various applications, such as intrusion detection, battlefield surveillance, and animal monitoring. One fundamental performance measure in those applications is the sensing coverage of WSNs. Insufficient coverage will significantly reduce the effectiveness of the applications. However, most existing studies on coverage assume that the sensing range of a sensor node is a disk, and the disk coverage model is too simplistic for many localization techniques. Moreover, there are some localization techniques of WSNs whose coverage model is non-disk, such as RSSI-based localization techniques. In this paper, we focus on detecting and recovering coverage holes of WSNs to enhance RSSI-based localization techniques whose coverage model is an ellipse. We propose an algorithm inspired by Voronoi tessellation and Delaunay triangulation to detect and recover coverage holes. Simulation results show that our algorithm can recover all holes and can reach any set coverage rate, up to 100% coverage.

Channel state information (CSI) has been recently shown to be useful in performing security attacks in public WiFi environments. By analyzing how CSI is affected by finger motions, CSI-based attacks can effectively reconstruct text-based passwords and locking patterns. This paper presents WiGuard, a novel system to protect sensitive on-screen input information in a public place. Our approach carefully exploits WiFi channel interference to introduce noise to attacker’s CSI measurements to reduce the success rate of CSI-based attacks. Our approach automatically detects when a CSI-based attack happens. We evaluate our approach by applying it to protect text-based passwords and pattern locks on mobile devices. Experimental results show that our approach is able to reduce the success rate of CSI-based attacks from 92–42% for text-based passwords and from 82–22% for pattern lock.

Localization is emerging as a fundamental component in wireless sensor network and is widely used in the fields of environmental monitoring, national defense and military, transportation, and so on. Current positioning system, however, can only locate an object's position in isotropy wireless sensor network with high accuracy but cannot locate it accurately in anisotropy wireless sensor network. Besides, past proposals only mentioned anisotropy to show that connectivity of network is different in each direction. However, how to quantify the degree of anisotropy is not clearly pointed out. This paper introduces NDSL (node density-based subregional localization), a positioning system that is used in anisotropy wireless sensor network. The network is divided into many subregions where the nodes density is relatively uniform and then corrects the single-hop distance for each beacon node to locate unknown nodes. We also use nodes distribution and signals distribution to build a model to evaluate the degree of anisotropy for anisotropy network. Through the analysis of the degree of anisotropy for different topologies, the results show that the model is consistent with the facts. Results from actual deployments and simulation experiments show that the accuracy of NDSL algorithm obviously improves compared with DV-Hop algorithm.

Localization is emerging as a fundamental component in wireless sensor network and is widely used in the field of environmental monitoring, national and military defense, transportation monitoring, and so on. Current localization methods, however, focus on how to improve accuracy without considering the robustness. Thus, the error will increase rapidly when nodes density and SNR (signal to noise ratio) have changed dramatically. This paper introduces CTLL, Cell-Based Transfer Learning Method for Localization in WSNs, a new way for localization which is robust to the variances of nodes density and SNR. The method combines samples transfer learning and SVR (Support Vector Regression) regression model to get a better performance of localization. Unlike past work, which considers that the nodes density and SNR are invariable, our design applies regional division and transfer learning to adapt to the variances of nodes density and SNR. We evaluate the performance of our method both on simulation and realistic deployment. The results show that our method increases accuracy and provides high robustness under a low cost.

Self-localization is one of the key technologies in the wireless sensor networks (WSN). Some traditional self-localization algorithms can provide a reasonable positioning accuracy only in a uniform and dense network, while for a nonuniform network the performance is not acceptable. In this paper, we presented a novel grid-based linear least squares (LLS) self-localization algorithm. The proposed algorithm uses the grid method to screen the anchors based on the distribution characteristic of a nonuniform network. Furthermore, by taking into consideration the quasi-uniform distribution of anchors in the area, we select suitable anchors to assist the localization. Simulation results demonstrate that the proposed algorithm can greatly enhance the localization accuracy of the anonymous nodes and impose less computation burden compared to traditional Trilateration and Multilateration.

As the underlying infrastructure of the Internet of Things (IoT), wireless sensor networks (WSNs) have been widely used in many applications. Network coding is a technique in WSNs to combine multiple channels of data in one transmission, wherever possible, to save node’s energy as well as increase the network throughput. So far most works on network coding are based on two assumptions to determine coding opportunities: (1) All the links in the network have the same transmission success rate; (2) Each link is bidirectional, and has the same transmission success rate on both ways. However, these assumptions may not be true in many actual WSNs—the wireless links among nodes are often subject to all kinds of disturbance, obstruction, etc., and may transmit with different success rates. This paper proposes a new routing strategy, named Adaptive Network Coding Routing (ANCR). ANCR firstly establishes a routing path with the traditional network coding routing (NCR), and then applies the neighborhood search algorithm to adaptively determine nodes’ coding opportunities based on the links’ transmission success rates, with the target of reducing the total number of transmission. The simulation results show that, in WSNs with different-success-rate links, ANCR can reduce the network delay by about 50%, and increase the network throughput by about 67%, compared with the traditional NCR.

An understanding of the changes of the rammed earth temperature of earthen ruins is important for protection of such ruins. To predict the rammed earth temperature pattern using the air temperature pattern of the monitoring data of earthen ruins, a pattern prediction method based on interesting pattern mining and correlation, called PPER, is proposed in this paper. PPER first finds the interesting patterns in the air temperature sequence and the rammed earth temperature sequence. To reduce the processing time, two pruning rules and a new data structure based on an R-tree are also proposed. Correlation rules between the air temperature patterns and the rammed earth temperature patterns are then mined. The correlation rules are merged into predictive rules for the rammed earth temperature pattern. Experiments were conducted to show the accuracy of the presented method and the power of the pruning rules. Moreover, the Ming Dynasty Great Wall dataset was used to examine the algorithm, and six predictive rules from the air temperature to rammed earth temperature based on the interesting patterns were obtained, with the average hit rate reaching 89.8%. The PPER and predictive rules will be useful for rammed earth temperature prediction in protection of earthen ruins.

The passive object localization (POL) problem in wireless sensor networks aims to determine the location of a target without any device attached for receiving or transmitting signal. This problem is challenging as there is very limited information available for deriving the target location. By combining the diffraction and scattering models, we propose a link sensing adaptive approach to POL, which first decides the target position attribute based on the signal strength and then localizes the target in different modes. We conduct rigorous localizability analyses and design a unit localization area scheme to achieve a higher level of localization accuracy. The efficacy of the proposed method is evaluated through comprehensive experiments in real life network environments.

The low-cost crystal oscillators in wireless sensor networks are prone to be affected by their working conditions such as voltage, temperature, and humidity. Such effect is often ignored by existing time synchronization solutions that typically assume the frequency error of a given node to be constant and hence adopt frequent timestamp exchanges, resulting in high energy consumptions. We propose a novel voltage-aware time synchronization (VATS) scheme that is inspired by the fact that the clock skew is highly correlated to voltage supplies. VATS features a two-phase process: (i) it first estimates the clock skew and updates the frequency error autonomously based on the local voltage level; (ii) it then adjusts the resynchronization intervals dynamically according to a given synchronization error controlling factor and the synchronization error accumulating rate to balance the calibration accuracy and cost. Since VATS leverages voltage measurements to assist clock skew estimation, it does not require frequent timestamp exchanges as in traditional schemes. Extensive simulation results illustrate the superior performance of the proposed method in terms of calculation accuracy, robustness, and reduced timestamp exchanges for energy saving.

When we encounter a malicious rumor or an infectious disease outbreak, immunizing k nodes of the relevant network with limited resources is always treated as an extremely effective method. The key challenge is how we can insulate limited nodes to minimize the propagation of those contagious things. In previous works, the best k immunised nodes are selected by learning the initial status of nodes and their strategies even if there is no feedback in the propagation process, which eventually leads to ineffective performance of their solutions. In this paper, we design a novel vaccines placement strategy for protecting much more healthy nodes from being infected by infectious nodes. The main idea of our solution is that we are not only utilizing the status of changing nodes as auxiliary knowledge to adjust our scheme, but also comparing the performance of vaccines in various transmission slots. Thus, our solution has a better chance to get more benefit from these limited vaccines. Extensive experiments have been conducted on several real-world data sets and the results have shown that our algorithm has a better performance than previous works.