Related papers: Robustness to Adversarial Attacks in Learning-Enab…

Adversarial attacks against neural networks in a regression setting are a critical yet understudied problem. In this work, we advance the state of the art by investigating adversarial attacks against regression networks and by formulating a…

Large Language Models' safety remains a critical concern due to their vulnerability to adversarial attacks, which can prompt these systems to produce harmful responses. In the heart of these systems lies a safety classifier, a computational…

Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsistent and incomprehensible predictions with humans at some…

Recent continual learning approaches have primarily focused on mitigating catastrophic forgetting. Nevertheless, two critical areas have remained relatively unexplored: 1) evaluating the robustness of proposed methods and 2) ensuring the…

This paper addresses a fundamental and important question in control: under what conditions does there fail to exist a robust control policy that keeps the state of a constrained linear system within a target set, despite bounded…

Congestion controllers (CCs) are critical to network performance, and yet their robustness under adverse conditions remains insufficiently understood. While recent learning-based CCs have demonstrated strong performance in controlled…

A cyber-physical system (CPS) is a tight coupling of computational resources, network communication, and physical processes. They are composed of a set of networked components, including sensors, actuators, control processing units, and…

Evolving attacks on the vulnerabilities of the computing systems demand novel defense strategies to keep pace with newer attacks. This report discusses previous works on side-channel attacks (SCAs) and defenses for cache-targeted and…

As the adoption of machine learning models increases, ensuring robust models against adversarial attacks is increasingly important. With unsupervised machine learning gaining more attention, ensuring it is robust against attacks is vital.…

Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily…

Networked-Control Systems (NCSs), a type of cyber-physical systems, consist of tightly integrated computing, communication and control technologies. While being very flexible environments, they are vulnerable to computing and networking…

Despite considerable efforts on making them robust, real-world AI-based systems remain vulnerable to decision based attacks, as definitive proofs of their operational robustness have so far proven intractable. Canonical robustness…

Upon the discovery of adversarial attacks, robust models have become obligatory for deep learning-based systems. Adversarial training with first-order attacks has been one of the most effective defenses against adversarial perturbations to…

Modern power systems face increasing vulnerability to sophisticated cyber-physical attacks beyond traditional N-1 contingency frameworks. Existing security paradigms face a critical bottleneck: efficiently identifying worst-case scenarios…

Autonomous cars are well known for being vulnerable to adversarial attacks that can compromise the safety of the car and pose danger to other road users. To effectively defend against adversaries, it is required to not only test autonomous…

A cyber-physical system (CPS) is expected to be resilient to more than one type of adversary. In this paper, we consider a CPS that has to satisfy a linear temporal logic (LTL) objective in the presence of two kinds of adversaries. The…

The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an…

The problem of adversarial examples, evasion attacks on machine learning classifiers, has proven extremely difficult to solve. This is true even when, as is the case in many practical settings, the classifier is hosted as a remote service…

Autonomous systems increasingly rely on machine learning techniques to transform high-dimensional raw inputs into predictions that are then used for decision-making and control. However, it is often easy to maliciously manipulate such…

Adversarial Training has proved to be an effective training paradigm to enforce robustness against adversarial examples in modern neural network architectures. Despite many efforts, explanations of the foundational principles underpinning…