相关论文: CS-GBA: A Critical Sample-based Gradient-guided Ba…

In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only offline data. Traditional methods often face difficulties in…

Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack…

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence…

The extensive adoption of Self-supervised learning(SSL) has led to an increased security threat from backdoor attacks. While existing research has mainly focused on backdoor attacks in image classification, there has been limited…

This work presents CaFA, a system for Cost-aware Feasible Attacks for assessing the robustness of neural tabular classifiers against adversarial examples realizable in the problem space, while minimizing adversaries' effort. To this end,…

LiDAR-based 3D object detection is widely used in safety-critical systems. However, these systems remain vulnerable to backdoor attacks that embed hidden malicious behaviors during training. A key limitation of existing backdoor attacks is…

Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing…

This chapter studies emerging cyber-attacks on reinforcement learning (RL) and introduces a quantitative approach to analyze the vulnerabilities of RL. Focusing on adversarial manipulation on the cost signals, we analyze the performance…

Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction. Gradient estimation is a critical step in black-box…

Backdoor attacks pose a significant security risk to graph learning models. Backdoors can be embedded into the target model by inserting backdoor triggers into the training dataset, causing the model to make incorrect predictions when the…

Recent studies have revealed that GNNs are highly susceptible to multiple adversarial attacks. Among these, graph backdoor attacks pose one of the most prominent threats, where attackers cause models to misclassify by learning the…

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Backdoor attack has emerged as a novel and concerning threat to AI security. These attacks involve the training of Deep Neural Network (DNN) on datasets that contain hidden trigger patterns. Although the poisoned model behaves normally on…

Deep Neural Networks (DNNs) are shown to be vulnerable to backdoor poisoning attacks, with most research focusing on digital triggers -- artificial patterns added to test-time inputs to induce targeted misclassification. Physical triggers,…

As reinforcement learning (RL) has achieved near human-level performance in a variety of tasks, its robustness has raised great attention. While a vast body of research has explored test-time (evasion) attacks in RL and corresponding…

Reinforcement learning algorithms are typically designed for discrete-time dynamics, even though the underlying real-world control systems are often continuous in time. In this paper, we study the problem of continuous-time reinforcement…

Constrained Reinforcement Learning (CRL) tackles sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints, which are often formulated as…

Offline Reinforcement Learning (RL) is a promising approach for next-generation wireless networks, where online exploration is unsafe and large amounts of operational data can be reused across the model lifecycle. However, the behavior of…

Traditional distributed backdoor attacks (DBA) in federated learning improve stealthiness by decomposing global triggers into sub-triggers, which however requires more poisoned data to maintian the attck strength and hence increases the…

Poison-only Clean-label Backdoor Attacks aim to covertly inject attacker-desired behavior into DNNs by merely poisoning the dataset without changing the labels. To effectively implant a backdoor, multiple \textbf{triggers} are proposed for…