Out-of-distribution (OOD) detection has attracted a large amount of attention from the machine learning research community in recent years due to its importance in deployed systems. Most of the previous studies focused on the detection of OOD samples in the multi-class classification task. However, OOD detection in the multi-label classification task remains an underexplored domain. In this research, we propose YolOOD - a method that utilizes concepts from the object detection domain to perform OOD detection in the multi-label classification task. Object detection models have an inherent ability to distinguish between objects of interest (in-distribution) and irrelevant objects (e.g., OOD objects) on images that contain multiple objects from different categories. These abilities allow us to convert a regular object detection model into an image classifier with inherent OOD detection capabilities with just minor changes. We compare our approach to state-of-the-art OOD detection methods and demonstrate YolOOD's ability to outperform these methods on a comprehensive suite of in-distribution and OOD benchmark datasets.
Model agnostic feature attribution algorithms (such as SHAP and LIME) are ubiquitous techniques for explaining the decisions of complex classification models, such as deep neural networks. However, since complex classification models produce superior performance when trained on low-level (or encoded) features, in many cases, the explanations generated by these algorithms are neither interpretable nor usable by humans. Methods proposed in recent studies that support the generation of human-interpretable explanations are impractical, because they require a fully invertible transformation function that maps the model's input features to the human-interpretable features. In this work, we introduce Latent SHAP, a black-box feature attribution framework that provides human-interpretable explanations, without the requirement for a fully invertible transformation function. We demonstrate Latent SHAP's effectiveness using (1) a controlled experiment where invertible transformation functions are available, which enables robust quantitative evaluation of our method, and (2) celebrity attractiveness classification (using the CelebA dataset) where invertible transformation functions are not available, which enables thorough qualitative evaluation of our method.
In recent years, various watermarking methods were suggested to detect computer vision models obtained illegitimately from their owners, however they fail to demonstrate satisfactory robustness against model extraction attacks. In this paper, we present an adaptive framework to watermark a protected model, leveraging the unique behavior present in the model due to a unique random seed initialized during the model training. This watermark is used to detect extracted models, which have the same unique behavior, indicating an unauthorized usage of the protected model's intellectual property (IP). First, we show how an initial seed for random number generation as part of model training produces distinct characteristics in the model's decision boundaries, which are inherited by extracted models and present in their decision boundaries, but aren't present in non-extracted models trained on the same data-set with a different seed. Based on our findings, we suggest the Robust Adaptive Watermarking (RAW) Framework, which utilizes the unique behavior present in the protected and extracted models to generate a watermark key-set and verification model. We show that the framework is robust to (1) unseen model extraction attacks, and (2) extracted models which undergo a blurring method (e.g., weight pruning). We evaluate the framework's robustness against a naive attacker (unaware that the model is watermarked), and an informed attacker (who employs blurring strategies to remove watermarked behavior from an extracted model), and achieve outstanding (i.e., >0.9) AUC values. Finally, we show that the framework is robust to model extraction attacks with different structure and/or architecture than the protected model.
Adversarial attacks against deep learning-based object detectors (ODs) have been studied extensively in the past few years. These attacks cause the model to make incorrect predictions by placing a patch containing an adversarial pattern on the target object or anywhere within the frame. However, none of prior research proposed a misclassification attack on ODs, in which the patch is applied on the target object. In this study, we propose a novel, universal, targeted, label-switch attack against the state-of-the-art object detector, YOLO. In our attack, we use (i) a tailored projection function to enable the placement of the adversarial patch on multiple target objects in the image (e.g., cars), each of which may be located a different distance away from the camera or have a different view angle relative to the camera, and (ii) a unique loss function capable of changing the label of the attacked objects. The proposed universal patch, which is trained in the digital domain, is transferable to the physical domain. We performed an extensive evaluation using different types of object detectors, different video streams captured by different cameras, and various target classes, and evaluated different configurations of the adversarial patch in the physical domain.
State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. However, their wide adoption in mission-critical contexts is hampered by two major weaknesses - their susceptibility to adversarial attacks and their opaqueness. The former raises concerns about the security and generalization of DNNs in real-world conditions, whereas the latter impedes users' trust in their output. In this research, we (1) examine the effect of adversarial robustness on interpretability and (2) present a novel approach for improving the interpretability of DNNs that is based on regularization of neural activation sensitivity. We evaluate the interpretability of models trained using our method to that of standard models and models trained using state-of-the-art adversarial robustness techniques. Our results show that adversarially robust models are superior to standard models and that models trained using our proposed method are even better than adversarially robust models in terms of interpretability.
Many challenging real-world problems require the deployment of ensembles multiple complementary learning models to reach acceptable performance levels. While effective, applying the entire ensemble to every sample is costly and often unnecessary. Deep Reinforcement Learning (DRL) offers a cost-effective alternative, where detectors are dynamically chosen based on the output of their predecessors, with their usefulness weighted against their computational cost. Despite their potential, DRL-based solutions are not widely used in this capacity, partly due to the difficulties in configuring the reward function for each new task, the unpredictable reactions of the DRL agent to changes in the data, and the inability to use common performance metrics (e.g., TPR/FPR) to guide the algorithm's performance. In this study we propose methods for fine-tuning and calibrating DRL-based policies so that they can meet multiple performance goals. Moreover, we present a method for transferring effective security policies from one dataset to another. Finally, we demonstrate that our approach is highly robust against adversarial attacks.
Adversarial attacks against deep learning-based object detectors have been studied extensively in the past few years. The proposed attacks aimed solely at compromising the models' integrity (i.e., trustworthiness of the model's prediction), while adversarial attacks targeting the models' availability, a critical aspect in safety-critical domains such as autonomous driving, have not been explored by the machine learning research community. In this paper, we propose NMS-Sponge, a novel approach that negatively affects the decision latency of YOLO, a state-of-the-art object detector, and compromises the model's availability by applying a universal adversarial perturbation (UAP). In our experiments, we demonstrate that the proposed UAP is able to increase the processing time of individual frames by adding "phantom" objects while preserving the detection of the original objects.
The Open Radio Access Network (O-RAN) is a new, open, adaptive, and intelligent RAN architecture. Motivated by the success of artificial intelligence in other domains, O-RAN strives to leverage machine learning (ML) to automatically and efficiently manage network resources in diverse use cases such as traffic steering, quality of experience prediction, and anomaly detection. Unfortunately, ML-based systems are not free of vulnerabilities; specifically, they suffer from a special type of logical vulnerabilities that stem from the inherent limitations of the learning algorithms. To exploit these vulnerabilities, an adversary can utilize an attack technique referred to as adversarial machine learning (AML). These special type of attacks has already been demonstrated in recent researches. In this paper, we present a systematic AML threat analysis for the O-RAN. We start by reviewing relevant ML use cases and analyzing the different ML workflow deployment scenarios in O-RAN. Then, we define the threat model, identifying potential adversaries, enumerating their adversarial capabilities, and analyzing their main goals. Finally, we explore the various AML threats in the O-RAN and review a large number of attacks that can be performed to materialize these threats and demonstrate an AML attack on a traffic steering model.
Deep learning-based facial recognition (FR) models have demonstrated state-of-the-art performance in the past few years, even when wearing protective medical face masks became commonplace during the COVID-19 pandemic. Given the outstanding performance of these models, the machine learning research community has shown increasing interest in challenging their robustness. Initially, researchers presented adversarial attacks in the digital domain, and later the attacks were transferred to the physical domain. However, in many cases, attacks in the physical domain are conspicuous, requiring, for example, the placement of a sticker on the face, and thus may raise suspicion in real-world environments (e.g., airports). In this paper, we propose Adversarial Mask, a physical adversarial universal perturbation (UAP) against state-of-the-art FR models that is applied on face masks in the form of a carefully crafted pattern. In our experiments, we examined the transferability of our adversarial mask to a wide range of FR model architectures and datasets. In addition, we validated our adversarial mask effectiveness in real-world experiments by printing the adversarial pattern on a fabric medical face mask, causing the FR system to identify only 3.34% of the participants wearing the mask (compared to a minimum of 83.34% with other evaluated masks).
Deep learning face recognition models are used by state-of-the-art surveillance systems to identify individuals passing through public areas (e.g., airports). Previous studies have demonstrated the use of adversarial machine learning (AML) attacks to successfully evade identification by such systems, both in the digital and physical domains. Attacks in the physical domain, however, require significant manipulation to the human participant's face, which can raise suspicion by human observers (e.g. airport security officers). In this study, we present a novel black-box AML attack which carefully crafts natural makeup, which, when applied on a human participant, prevents the participant from being identified by facial recognition models. We evaluated our proposed attack against the ArcFace face recognition model, with 20 participants in a real-world setup that includes two cameras, different shooting angles, and different lighting conditions. The evaluation results show that in the digital domain, the face recognition system was unable to identify all of the participants, while in the physical domain, the face recognition system was able to identify the participants in only 1.22% of the frames (compared to 47.57% without makeup and 33.73% with random natural makeup), which is below a reasonable threshold of a realistic operational environment.