Related papers: Collaborative Shadows: Distributed Backdoor Attack…

While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive…

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

Large language model multi-agent systems (LLM-MAS) offer a promising paradigm for harnessing collective intelligence to achieve more advanced forms of AI behaviour. While recent studies suggest that LLM-MAS can outperform LLM single-agent…

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…

Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm…

Current backdoor defense methods are evaluated against a single attack at a time. This is unrealistic, as powerful machine learning systems are trained on large datasets scraped from the internet, which may be attacked multiple times by one…

Recent advances in large language models (LLMs) have raised concerns about jailbreaking attacks, i.e., prompts that bypass safety mechanisms. This paper investigates the use of multi-agent LLM systems as a defence against such attacks. We…

The increasing operational reliance on complex Multi-Agent Systems (MAS) across safety-critical domains necessitates rigorous adversarial robustness assessment. Modern MAS are inherently heterogeneous, integrating conventional Multi-Agent…

Multi-agent coordination studies the underlying mechanism enabling the trending spread of diverse multi-agent systems (MAS) and has received increasing attention, driven by the expansion of emerging applications and rapid AI advances. This…

The widespread adoption of open-source software (OSS) has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models…

The objective in this paper is to study and develop conditions for a network of multi-agent cyber-physical systems (MAS) where a malicious adversary can utilize vulnerabilities in order to ensure and maintain cyber attacks undetectable. We…

Large language models (LLMs) have demonstrated strong reasoning, planning, and communication abilities, enabling them to operate as autonomous agents in open environments. While single-agent systems remain limited in adaptability and…

As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previous work introduced control evaluations, an adversarial…

With the rapid advancement of large models (LMs), the development of general-purpose intelligent agents powered by LMs has become a reality. It is foreseeable that in the near future, LM-driven general AI agents will serve as essential…

LLM-based multi-agent systems (LLM-MAS), in which autonomous AI agents cooperate to solve tasks, are gaining increasing attention. For such systems to be deployed in society, agents must be able to establish cooperation and coordination…

Traditional, centralized security tools often miss adaptive, multi-vector attacks. We present the Multi-Agent LLM Cyber Defense Framework (MALCDF), a practical setup where four large language model (LLM) agents-Detection, Intelligence,…

Distributed multi-agent optimization (DMAO) enables the scalable control and coordination of a large population of edge resources in complex multi-agent environments. Despite its great scalability, DMAO is prone to cyber attacks as it…

The rapid advancement of large language models (LLMs) has led to the rise of LLM-based agents. Recent research shows that multi-agent systems (MAS), where each agent plays a specific role, can outperform individual LLMs. However,…

Federated learning is a promising approach for training machine learning models while preserving data privacy. However, its distributed nature makes it vulnerable to backdoor attacks, particularly in NLP tasks, where related research…

As large language models (LLMs) are increasingly deployed in healthcare, ensuring their safety, particularly within collaborative multi-agent configurations, is paramount. In this paper we introduce MedSentry, a benchmark comprising 5 000…