Related papers: GroupGuard: A Framework for Modeling and Defending…

This paper presents an adversary detection mechanism and a resilient control framework for multi-agent systems under spatiotemporal constraints. Safety in multi-agent systems is typically addressed under the assumption that all agents…

Recent developments in adversarial machine learning have highlighted the importance of building robust AI systems to protect against increasingly sophisticated attacks. While frameworks like AI Guardian are designed to defend against these…

Large scale cloud networks consist of distributed networking and computing elements that process critical information and thus security is a key requirement for any environment. Unfortunately, assessing the security state of such networks…

Collusion among autonomous agents poses a critical security threat in embodied multi-agent systems (MAS), where coordinated behaviors can deviate from global objectives and lead to real-world consequences. Existing defenses, primarily based…

The rapid proliferation of AI-Generated Images (AIGIs) has introduced severe risks of misinformation, making AIGI detection a critical yet challenging task. While traditional detection paradigms mainly rely on low-level features, recent…

The proliferation of open-source software (OSS) has made software supply chains prime targets for attacks like Package Confusion, where adversaries publish malicious packages with names deceptively similar to legitimate ones. To protect…

Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web,…

Machine learning (ML) underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box…

Recent studies in multi-agent communicative reinforcement learning (MACRL) have demonstrated that multi-agent coordination can be greatly improved by allowing communication between agents. Meanwhile, adversarial machine learning (ML) has…

Prompt injection attacks pose a critical threat to large language models (LLMs), enabling goal hijacking and data leakage. Prompt guard models, though effective in defense, suffer from over-defense -- falsely flagging benign inputs as…

In this paper, we investigate a multi-agent target guarding problem in which a single defender seeks to capture multiple attackers aiming to reach a high-value target area. In contrast to previous studies, the attackers herein are assumed…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions. However, when deploying trained communicative agents in a real-world application where noise and…

Multimodal large language models (MLLMs) have revolutionized vision-language understanding but remain vulnerable to multimodal jailbreak attacks, where adversarial inputs are meticulously crafted to elicit harmful or inappropriate…

Large Language Models (LLMs) & Generative AI are transforming cybersecurity, enabling both advanced defenses and new attacks. Organizations now use LLMs for threat detection, code review, and DevSecOps automation, while adversaries leverage…

Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…

The use of machine learning (ML) has become increasingly prevalent in various domains, highlighting the importance of understanding and ensuring its safety. One pressing concern is the vulnerability of ML applications to model stealing…

Model poisoning attacks pose a significant security threat to Federated Learning (FL). Most existing model poisoning attacks rely on collusion, requiring adversarial clients to coordinate by exchanging local benign models and synchronizing…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Foundation model-based agents are increasingly used to automate complex tasks, enhancing efficiency and productivity. However, their access to sensitive resources and autonomous decision-making also introduce significant security risks,…