Related papers: Fine-Grained Iterative Adversarial Attacks with Li…
Deep neural networks are vulnerable to adversarial attacks. Most $L_{0}$-norm based white-box attacks craft perturbations by the gradient of models to the input. Since the computation cost and memory limitation of calculating the Hessian…
Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…
In the realm of efficient on-device learning under extreme memory and computation constraints, a significant gap in successful approaches persists. Although considerable effort has been devoted to efficient inference, the main obstacle to…
Federated adversarial training can effectively complement adversarial robustness into the privacy-preserving federated learning systems. However, the high demand for memory capacity and computing power makes large-scale federated…
We evaluate the autonomous cyber-attack capabilities of frontier AI models on two purpose-built cyber ranges-a 32-step corporate network attack and a 7-step industrial control system attack-that require chaining heterogeneous capabilities…
As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…
Significant work is being done to develop the math and tools necessary to build provable defenses, or at least bounds, against adversarial attacks of neural networks. In this work, we argue that tools from control theory could be leveraged…
Deep neural networks are vulnerable to adversarial examples that mislead the models with imperceptible perturbations. Though adversarial attacks have achieved incredible success rates in the white-box setting, most existing adversaries…
Projected Gradient Descent (PGD) based adversarial training has become one of the most prominent methods for building robust deep neural network models. However, the computational complexity associated with this approach, due to the…
Machine learning techniques are currently used extensively for automating various cybersecurity tasks. Most of these techniques utilize supervised learning algorithms that rely on training the algorithm to classify incoming data into…
Recent studies identify that Deep learning Neural Networks (DNNs) are vulnerable to subtle perturbations, which are not perceptible to human visual system but can fool the DNN models and lead to wrong outputs. A class of adversarial attack…
The expanding computational costs and limited resources underscore the critical need for budgeted-iteration training, which aims to achieve optimal learning within predetermined iteration budgets. While learning rate schedules fundamentally…
In distributed multiple-input multiple-output (D-MIMO) networks, power control is crucial to optimize the spectral efficiencies of users and max-min fairness (MMF) power control is a commonly used strategy as it satisfies uniform…
In this article I describe a research agenda for securing machine learning models against adversarial inputs at test time. This article does not present results but instead shares some of my thoughts about where I think that the field needs…
The impressive success of Generative Adversarial Networks (GANs) is often overshadowed by the difficulties in their training. Despite the continuous efforts and improvements, there are still open issues regarding their convergence…
Adversarial machine learning concerns situations in which learners face attacks from active adversaries. Such scenarios arise in applications such as spam email filtering, malware detection and fake image generation, where security methods…
Many state-of-the-art adversarial training methods for deep learning leverage upper bounds of the adversarial loss to provide security guarantees against adversarial attacks. Yet, these methods rely on convex relaxations to propagate lower…
In this paper, we study the robustness of classical deep hedging strategies under distributional shifts by leveraging the concept of adversarial attacks. We first demonstrate that standard deep hedging models are highly vulnerable to small…
Based on the significant improvement of model robustness by AT (Adversarial Training), various variants have been proposed to further boost the performance. Well-recognized methods have focused on different components of AT (e.g., designing…
Adversarial ranking attacks have gained increasing attention due to their success in probing vulnerabilities, and, hence, enhancing the robustness, of neural ranking models. Conventional attack methods employ perturbations at a single…