As deep neural networks constantly improve and provide state-of-the-art solutions to various problems, deployment of these models becomes more common, and so does the importance of protecting these models against malicious attacks attempting to replicate these models. In this paper, we present a novel zero-knowledge method for attacking and stealing knowledge from deep neural networks. Our method utilizes unlabeled data and the predictions of the mentor model we would like to steal. The presented method targets the most protected models which reveal only the minimal amount of information, i.e., the predicted label. We assume no access to any internal information about the model, and no access to the training data. The presented method improves the SOTA performance of attacking protected neural network models. The results show that all classification neural networks are vulnerable to the presented attack method, and any attacker can effectively replicate these models without having access to their architecture, parameters, training data, or softmax outputs.

Deep neural networks (NNs) trained on hyperspectral images are employed typically for the classification of new images collected from the same sensor, assuming similar characteristics to those of the training images. Creating, however, high-quality ground truth (GT) for training is rather complex, especially when attempting to classify multi-temporal images over seasonal changes. To overcome this difficulty, we propose a novel method that utilizes an additional, one-time collection of hyperspectral FENIX images in the Spring along with ground observations from the end of the Fall. The hyperspectral data are then used for simulation of GT for training. At the same time, the field campaign allows for fine-tuning of the NN to achieve enhanced, multi-seasonal hyperspectral image classification. Indeed, we demonstrate how the proposed method successfully classifies new VEN μS images obtained during different seasons.

In recent years, the topic of explainable machine learning (ML) has been extensively researched. Up until now, this research focused on regular ML users use-cases such as debugging a ML model. This paper takes a different posture and show that adversaries can leverage explainable ML to bypass multi-feature types malware classifiers. Previous adversarial attacks against such classifiers only add new features and not modify existing ones to avoid harming the modified malware executable's functionality. Current attacks use a single algorithm that both selects which features to modify and modifies them blindly, treating all features the same. In this paper, we present a different approach. We split the adversarial example generation task into two parts: First we find the importance of all features for a specific sample using explainability algorithms, and then we conduct a feature-specific modification, feature-by-feature. In order to apply our attack in black-box scenarios, we introduce the concept of transferability of explainability, that is, applying explainability algorithms to different classifiers using different features subsets and trained on different datasets still result in a similar subset of important features. We conclude that explainability algorithms can be leveraged by adversaries and thus the advocates of training more interpretable classifiers should consider the trade-off of higher vulnerability of those classifiers to adversarial attacks.

This paper presents a novel scheme, based on a unique combination of genetic algorithms (GAs) and deep learning (DL), for the automatic reconstruction of Portuguese tile panels, a challenging real-world variant of the jigsaw puzzle problem (JPP) with important national heritage implications. Specifically, we introduce an enhanced GA-based puzzle solver, whose integration with a novel DL-based compatibility measure (DLCM) yields state-of-the-art performance, regarding the above application. Current compatibility measures consider typically (the chromatic information of) edge pixels (between adjacent tiles), and help achieve high accuracy for the synthetic JPP variant. However, such measures exhibit rather poor performance when applied to the Portuguese tile panels, which are susceptible to various real-world effects, e.g., monochromatic panels, non-squared tiles, edge degradation, etc. To overcome such difficulties, we have developed a novel DLCM to extract high-level texture/color statistics from the entire tile information.

Training a deep neural network for classification constitutes a major problem in remote sensing due to the lack of adequate field data. Acquiring high-resolution ground truth (GT) by human interpretation is both cost-ineffective and inconsistent. We propose, instead, to utilize high-resolution, hyperspectral images for solving this problem, by unmixing these images to obtain reliable GT for training a deep network. Specifically, we simulate GT from high-resolution, hyperspectral FENIX images, and use it for training a convolutional neural network (CNN) for pixel-based classification. We show how the model can be transferred successfully to classify new mid-resolution VENμS imagery.

As state-of-the-art deep neural networks are deployed at the core of more advanced Al-based products and services, the incentive for copying them (i.e., their intellectual properties) by rival adversaries is expected to increase considerably over time. The best way to extract or steal knowledge from such networks is by querying them using a large dataset of random samples and recording their output, followed by training a student network to mimic these outputs, without making any assumption about the original networks. The most effective way to protect against such a mimicking attack is to provide only the classification result, without confidence values associated with the softmax layer.In this paper, we present a novel method for generating composite images for attacking a mentor neural network using a student model. Our method assumes no information regarding the mentor's training dataset, architecture, or weights. Further assuming no information regarding the mentor's softmax output values, our method successfully mimics the given neural network and steals all of its knowledge. We also demonstrate that our student network (which copies the mentor) is impervious to watermarking protection methods, and thus would not be detected as a stolen model.Our results imply, essentially, that all current neural networks are vulnerable to mimicking attacks, even if they do not divulge anything but the most basic required output, and that the student model which mimics them cannot be easily detected and singled out as a stolen copy using currently available techniques.

In this paper, we present a novel method of differentiating known from previously unseen malware families. We utilize transfer learning by learning compact file representations that are used for a new classification task between previously seen malware families and novel ones. The learned file representations are composed of static and dynamic features of malware files and are invariant to small modifications that do not change the malware functionality. Using an extensive dataset that consists of thousands of variants of malicious files, we were able to achieve 97.7% accuracy when classifying between seen and unseen malware families. Our method provides an important focalizing tool for cybersecurity researchers and greatly improves the overall ability to adapt to the fast-moving pace of the current threat landscape.

This paper presents a novel deep learning based method for automatic malware signature generation and classification. The method uses a deep belief network (DBN), implemented with a deep stack of denoising autoencoders, generating an invariant compact representation of the malware behavior. While conventional signature and token based methods for malware detection do not detect a majority of new variants for existing malware, the results presented in this paper show that signatures generated by the DBN allow for an accurate classification of new malware variants. Using a dataset containing hundreds of variants for several major malware families, our method achieves 98.6% classification accuracy using the signatures generated by the DBN. The presented method is completely agnostic to the type of malware behavior that is logged (e.g., API calls and their parameters, registry entries, websites and ports accessed, etc.), and can use any raw input from a sandbox to successfully train the deep neural network which is used to generate malware signatures.

In this paper we introduce new types of square-piece jigsaw puzzles, where in addition to the unknown location and orientation of each piece, a piece might also need to be flipped. These puzzles, which are associated with a number of real world problems, are considerably harder, from a computational standpoint. Specifically, we present a novel generalized genetic algorithm (GA)-based solver that can handle puzzle pieces of unknown location and orientation (Type 2 puzzles) and (two-sided) puzzle pieces of unknown location, orientation, and face (Type 4 puzzles). To the best of our knowledge, our solver provides a new state-of-the-art, solving previously attempted puzzles faster and far more accurately, handling puzzle sizes that have never been attempted before, and assembling the newly introduced two-sided puzzles automatically and effectively. This paper also presents, among other results, the most extensive set of experimental results, compiled as of yet, on Type 2 puzzles.

In this paper we describe the problem of painter classification, and propose a novel hybrid approach incorporating genetic algorithms (GA) and deep restricted Boltzmann machines (RBM). Given a painting, we extract features using both generic image processing (IP) functions (e.g., fractal dimension, Fourier spectra coefficients, texture coefficients, etc.) and unsupervised deep learning (using deep RBMs). We subsequently compare several supervised learning techniques for classification using the extracted features as input. The results show that the weighted nearest neighbor (WNN) method, for which the weights are evolved using GA, outperforms both a support vector machine (SVM) classifier and a standard nearest neighbor classifier, achieving over 90% classification accuracy for the 3-painter problem (an improvement of over 10% relatively to previous results due to standard feature extraction only).

In this paper we propose the first genetic algorithm (GA)-based solver for jigsaw puzzles of unknown puzzle dimensions and unknown piece location and orientation. Our solver uses a novel crossover technique, and sets a new state-of-the-art in terms of the puzzle sizes solved and the accuracy obtained. The results are significantly improved, even when compared to previous solvers assuming known puzzle dimensions. Moreover, the solver successfully contends with a mixed bag of multiple puzzle pieces, assembling simultaneously all puzzles.

This paper demonstrates the use of genetic algorithms for evolving: 1) a grandmaster-level evaluation function, and 2) a search mechanism for a chess program, the parameter values of which are initialized randomly. The evaluation function of the program is evolved by learning from databases of (human) grandmaster games. At first, the organisms are evolved to mimic the behavior of human grandmasters, and then these organisms are further improved upon by means of coevolution. The search mechanism is evolved by learning from tactical test suites. Our results show that the evolved program outperforms a two-time world computer chess champion and is at par with the other leading computer chess programs.

This paper describes the problem of painter classification. We propose solving the problem by using genetic algorithms, which yields very promising results. The proposed methodology combines dimensionality reduction (via image preprocessing) and evolutionary computation techniques, by representing preprocessed data as a chromosome for a genetic algorithm (GA). The preprocessing of our scheme incorporates a diverse set of complex features (e.g., fractal dimension, Fourier spectra coefficients, and texture). The training phase of the GA employs a weighted nearest neighbor (NN) algorithm. We provide initial promising results for the 2- and 3-class cases, which offer significant improvement in comparison to a standard nearest neighbor classifier.

In this paper we propose the first effective automated, genetic algorithm (GA)-based jigsaw puzzle solver. We introduce a novel procedure of merging two "parent" solutions to an improved "child" solution by detecting, extracting, and combining correctly assembled puzzle segments. The solver proposed exhibits state-of-the-art performance solving previously attempted puzzles faster and far more accurately, and also puzzles of size never before attempted. Other contributions include the creation of a benchmark of large images, previously unavailable. We share the data sets and all of our results for future testing and comparative evaluation of jigsaw puzzle solvers.

In this paper we present a genetic algorithm (GA)-based approach for the stereo matching problem. More precisely, the approach presented is a combination of a simple dynamic programming algorithm, commonly used for stereo matching, with a practical GA-based optimization scheme. The performance of our scheme was evaluated on standard test data of the Middlebury benchmark. Specifically, the number of incorrect disparities on these data decreases by approximately 20% in comparison to the original approach (without the use of a GA).

This paper demonstrates the use of genetic algorithms for evolving a grandmaster-level evaluation function for a chess program. This is achieved by combining supervised and unsupervised learning. In the supervised learning phase the organisms are evolved to mimic the behavior of human grandmasters, and in the unsupervised learning phase these evolved organisms are further improved upon by means of coevolution.

In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function's parameters for computer chess. Our results show that using an appropriate mentor, we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Computer Chess Champion. This performance gain is achieved by evolving a program with a smaller number of parameters in its evaluation function to mimic the behavior of a superior mentor which uses a more extensive evaluation function. In principle, our mentor-assisted approach could be used in a wide range of problems for which appropriate mentors are available.