Related papers: OMNI-LEAK: Orchestrator Multi-Agent Network Induce…
TThis paper argues that \textbf{a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems (LLM-MAS)}. These systems, which consist of multiple LLM-powered agents working…
AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…
Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the…
Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic…
System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…
The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. However, the evolving nature of…
Recent advancements in Web AI agents have demonstrated remarkable capabilities in addressing complex web navigation tasks. However, emerging research shows that these agents exhibit greater vulnerability compared to standalone Large…
The growing use of large language model (LLM)-based conversational agents to manage sensitive user data raises significant privacy concerns. While these agents excel at understanding and acting on context, this capability can be exploited…
Multi-agent debate (MAD) systems leverage collaborative interactions among large language models (LLMs) agents to improve reasoning capabilities. While recent studies have focused on increasing the accuracy and scalability of MAD systems,…
Federated Learning (FL) is increasingly being adopted in military collaborations to develop Large Language Models (LLMs) while preserving data sovereignty. However, prompt injection attacks-malicious manipulations of input prompts-pose new…
Current evaluations of tool-integrated LLM agents typically focus on end-to-end tool-usage evaluation while neglecting their stability. This limits their real-world applicability, as various internal or external factors can cause agents to…
The generalization capabilities of Large Language Models (LLMs) have led to their widespread deployment across various applications. However, this increased adoption has introduced several security threats, notably in the forms of…
Modern Security Operations Centers struggle with alert fatigue, fragmented tooling, and limited cross-source event correlation. Challenges that current Security Information Event Management and Extended Detection and Response systems only…
Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…
Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly…
Multi-agent systems powered by large language models are advancing rapidly, yet the tension between mutual trust and security remains underexplored. We introduce and empirically validate the Trust-Vulnerability Paradox (TVP): increasing…
With the prosperity of large language models (LLMs), powerful LLM-based intelligent agents have been developed to provide customized services with a set of user-defined tools. State-of-the-art methods for constructing LLM agents adopt…
Safety concerns in large language models (LLMs) have gained significant attention due to their exposure to potentially harmful data during pre-training. In this paper, we identify a new safety vulnerability in LLMs: their susceptibility to…
LLM-based agents have recently attracted significant attention due to their ability to autonomously invoke relevant tools to accomplish complex tasks. However, recent studies have shown that these agents face severe security risks, which…
Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or…