Search

A novel Rubik’s cube based pixel level scrambling and simple XOR based diffusion is proposed in this paper to safely transmit multimedia information (images) through an untrusted channel, such as adaptive image content (i.e., plain image related) based initial random value generation is introduced to achieve high plain image sensitivity in order to overcome plain image related attacks. From this random value, the initial vectors of Henon map is obtained and this is iterated to obtain the key sequences to be applied over the Rubik’s cube row and column confusion processes. Also, the same random seed is involved in the key generation process based on prime factorization to be applied in diffusion. For each and every encryption of different plain image, the random list is changed dynamically and it is shown that the CIERPF method is secure against differential attacks. The CIERPF method is checked against various simulations to illustrate the security level of the technique. From the simulations, it is shown that the proposed methodology has good key space, high key sensitivity, and uniform distribution of cipher image pixels. Also differential cryptanalysis is performed for the proposed cryptosystem to prove its effectiveness towards differential attacks.

We introduce CyBERT, a cybersecurity feature claims classifier based on bidirectional encoder representations from transformers and a key component in our semi-automated cybersecurity vetting for industrial control systems (ICS). To train CyBERT, we created a corpus of labeled sequences from ICS device documentation collected across a wide range of vendors and devices. This corpus provides the foundation for fine-tuning BERT’s language model, including a prediction-guided relabeling process. We propose an approach to obtain optimal hyperparameters, including the learning rate, the number of dense layers, and their configuration, to increase the accuracy of our classifier. Fine-tuning all hyperparameters of the resulting model led to an increase in classification accuracy from 76% obtained with BertForSequenceClassification’s original architecture to 94.4% obtained with CyBERT. Furthermore, we evaluated CyBERT for the impact of randomness in the initialization, training, and data-sampling phases. CyBERT demonstrated a standard deviation of ±0.6% during validation across 100 random seed values. Finally, we also compared the performance of CyBERT to other well-established language models including GPT2, ULMFiT, and ELMo, as well as neural network models such as CNN, LSTM, and BiLSTM. The results showed that CyBERT outperforms these models on the validation accuracy and the F1 score, validating CyBERT’s robustness and accuracy as a cybersecurity feature claims classifier.

Systematic design and verification of advanced control strategies for complex systems under uncertainty largely remains an open problem. Despite the promise of black-box optimization methods for automated controller tuning, they generally lack formal guarantees on the solution quality, which is especially important in the control of safety-critical systems. This letter focuses on obtaining closed-loop performance guarantees for automated controller tuning, which can be formulated as a black-box optimization problem under uncertainty. We use recent advances in non-convex scenario theory to provide a distribution-free bound on the probability of the closed-loop performance measures. To mitigate the computational complexity of the data-driven scenario optimization method, we restrict ourselves to a discrete set of candidate tuning parameters. We propose to generate these candidates using constrained Bayesian optimization run multiple times from different random seed points. We apply the proposed method for tuning an economic nonlinear model predictive controller for a semibatch reactor modeled by seven highly nonlinear differential equations.

Offloading cellular traffic through Opportunistic Mobile Networks, also known as opportunistic offloading has been proposed as a promising way to relieve the overload of cellular networks. The efficiency of such opportunistic offloading is highly determined by the selection of initial seeds. With considering both the freshness of the content and the cost of transmission from the cellular network to the initial seeds, this paper defines a novel freshness-aware seed selection optimization problem to find both the optimal number of initial seeds and the maximum overall content utility. To solve the optimization problem, the optimal strategy is first analyzed, and then two seed selection methods: the greedy seed selection method and the decay-based seed selection method are proposed to find the optimal number of initial seeds to maximize the overall content utility. The greedy seed selection method iteratively selects nodes with the maximum Freshness Centrality value as initial seeds. To further improve the performance, the decay-based seed selection method selects initial seeds who are far apart and important in theirs local structure. Extensive real trace-driven simulations are conducted to evaluate the performance of our proposed seed selection methods. The results show that as expected the proposed decay-based seed selection method is superior to the proposed greedy seed selection method and the random seed selection method, not only in the Infocom 06 trace, but also in the MIT Reality trace.

The reliability and efficiency of a physically unclonable function (PUF) considerably depends on that of the random seed number generation process in the target hardware technology. Among the proposed hardware PUF techniques, flash memory-based approaches have several advantages because of the widespread use of flash memories in electronic devices. The operations of the flash memories such as read, program, and erase have been utilized to generate the random number based on their random process variations. In this work, we propose a random number generation method for the flash memory-based hardware PUF applications that utilize the intrinsic erase-suspend operation in modern flash memory devices. Unlike the conventional methods, the proposed method does not require any modification of the device or additional peripheral circuitry to control the operations. We evaluate the proposed method from the perspective of reliability and efficiency. The experimental results show that the proposed method can generate a 16-bit random number in 1 ms approximately while maintaining greater than 95 % reproductivity of the random number.

To visually label the copyright of 2D CAD (Computer aided design) engineering graphics, a reversible visible watermarking based on graphics fusion is proposed. For a given watermark graphics, the lines are first converted into polylines, and a random perturbation is performed to each vertex by using a random seed. Secondly, the host graphics are equally divided into multiple regions, and then the centers of these regions are calculated. The center of each watermark graphics is aligned with the center of each region. After that, the watermark graphics are scaled to be suitable for the size of these regions. Finally, the watermark graphics are iteratively embedded by fusing the host graphics and the watermark graphics. The host graphics can be completely recovered from the fused graphics by the authorized users who know the secret key. Experimental results validate its effectiveness, and the analysis demonstrates that it has a certain robustness against translation, rotation, scaling, and entity deletion.

Formal verification and analysis of a crypto hardware requires a formal specification, formal proof of equivalence of the specification with the hardware realization. Pseudo Random Number Generator hardware in Verilog RTL or equivalent has an entropy source for random seed, crypto algorithms and processing unit, authenticated access depicting static behavior; and dynamic finite state machines (FSM) for data flow control, fault/error checks and recovery. This paper focusses on a unified, transitive, compositional formal verification and analysis of a FPGA based PRNG with statistical methods, quantitative physical measurements based analysis, symbolic logical equivalence and model checks, and properties verification.

Big data analysis for accurate predictions requires adherence to systematic procedures. This study shows an entire data analysis phase from the data collection to model evaluation using the Long Short-Term memory(LSTM) for cryptocurrency price prediction. Three different coin prices are directly collected from the CoinMarketCap in nearly real-time by applying the web scraping technique. The LSTM model trained with this data varying random seed or static seed parameters to find optimal conditions, leading to better accuracy of the LSTM model. Our model evaluated their accuracy in terms of MAE, RMSE, and SMAPE indicators. As a result of this experiment, most of the best candidate parameters are classified at the fixed seed trail in terms of the RMSE for Bit coin, Ethereum, and Lite Coin.

The problem of automatic monitoring the deforestation process is considered for efficient prevention of illegal deforestation. Image segmentation model on the basis of U-Net family of deep neural networks (DNNs) was created. The forest/deforestation dataset was collected by parsing areas of Ukrainian forestries, where satellite images of 512×512 pixels contain areas with forest, deforestation, and other areas. The dataset with satellite imagery and segmented masks was uploaded at GitHub repository where it is available with the correspondent code for distributed training on tensor processing units (TPU). To overcome the imbalance of created dataset the hybrid loss function was created and tested in the training environment. K-fold cross validation and numerous runs for different random seeds were conducted to prove the model and dataset usefulness and stability during the training and validation process. The following asymptotic values of intersection over union (IOU) mean $(IOU_{mean})$ and standard deviation $(IOU_{std})$ were obtained after more than 100 epochs: $IOU_{mean}^{kfold}=0.52, IOU_{std}^{kfold}=0.03$ for cross-validation, and $IOU_{mean}^{random}=0.51, IOU_{std}^{random}=0.03$ for various random seed initialization. These results demonstrate that variation of images in the dataset and randomness of initialization have no significant effect on model performance, but the future research will be needed in the view of the possible increase of datasets where performance could be improved by the larger data representation, but some decrease of performance could be observed due to possible wider data variability. It is especially important for deployment of U-Net-like DNNS on devices with the limited computational resources for Edge Computing layer.

Classical molecular dynamics is a computer simulation technique that is in widespread use across many areas of science, from physics and chemistry to materials, biology, and medicine. The method continues to attract criticism due its oft-reported lack of reproducibility which is in part due to a failure to submit it to reliable uncertainty quantification (UQ). Here we show that the uncertainty arises from a combination of (i) the input parameters and (ii) the intrinsic stochasticity of the method controlled by the random seeds. To illustrate the situation, we make a systematic UQ analysis of a widely used molecular dynamics code (NAMD), applied to estimate binding free energy of a ligand-bound to a protein. In particular, we replace the usually fixed input parameters with random variables, systematically distributed about their mean values, and study the resulting distribution of the simulation output. We also perform a sensitivity analysis, which reveals that, out of a total of 175 parameters, just six dominate the variance in the code output. Furthermore, we show that binding energy calculations dampen the input uncertainty, in the sense that the variation around the mean output free energy is less than the variation around the mean of the assumed input distributions, if the output is ensemble-averaged over the random seeds. Without such ensemble averaging, the predicted free energy is five times more uncertain. The distribution of the predicted properties is thus strongly dependent upon the random seed. Owing to this substantial uncertainty, robust statistical measures of uncertainty in molecular dynamics simulation require the use of ensembles in all contexts.

Polyculture farming is a sustainable farming technique based on synergistic interactions between differing plant types that make them more resistant to diseases and pests and better able to retain water. Reduced uniformity can reduce use of pesticides, fertilizer, and water, but is more labor intensive and more challenging to automate. We describe a scaled physical testbed (1.5m×3.0m) that uses a high resolution camera and soil sensors to monitor polyculture plants to facilitate tuning of plant growth, companion effects, and irrigation parameters for a first-order garden simulator. We use this simulator to develop a novel seed placement algorithm that increases coverage and diversity, and a learned pruning policy. In simulation experiments, the seed placement algorithm yields 60% more coverage and 10% more diversity than random seed placement and the learned pruning policy runs 1000X faster than a procedural lookahead policy to achieve high leaf coverage and plant diversity on adversarial gardens that include plant species with diverse growth rates. These models and policies provide the groundwork for a fully-automated system under development. Code, datasets and supplementary material can be found at https://github.com/BerkeleyAutomation/AlphaGarden/.

Recent work has shown that fine-tuning large networks is surprisingly sensitive to changes in random seed(s). We explore the implications of this phenomenon for model fairness across demographic groups in clinical prediction tasks over electronic health records (EHR) in MIMIC-III -- the standard dataset in clinical NLP research. Apparent subgroup performance varies substantially for seeds that yield similar overall performance, although there is no evidence of a trade-off between overall and subgroup performance. However, we also find that the small sample sizes inherent to looking at intersections of minority groups and somewhat rare conditions limit our ability to accurately estimate disparities. Further, we find that jointly optimizing for high overall performance and low disparities does not yield statistically significant improvements. Our results suggest that fairness work using MIMIC-III should carefully account for variations in apparent differences that may arise from stochasticity and small sample sizes., Comment: Accepted for publication at NAACL 2021

We study goodness-of-fit and independence testing of discrete distributions in a setting where samples are distributed across multiple users. The users wish to preserve the privacy of their data while enabling a central server to perform the tests. Under the notion of local differential privacy, we propose simple, sample-optimal, and communication-efficient protocols for these two questions in the noninteractive setting, where in addition users may or may not share a common random seed. In particular, we show that the availability of shared (public) randomness greatly reduces the sample complexity. Underlying our public-coin protocols are privacy-preserving mappings which, when applied to the samples, minimally contract the distance between their respective probability distributions., To appear in the Special Issue on Privacy and Security of Information Systems of the IEEE Journal on Selected Areas in Information Theory (JSAIT), 2021. Journal version of the AISTATS'19 paper "Test without Trust: Optimal Locally Private Distribution Testing" (arXiv:1808.02174), which it extends and supersedes