Related papers: Teams of LLM Agents can Exploit Zero-Day Vulnerabi…

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…

LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi-turn user-agent-environment interactions to achieve…

Computer-use agent (CUA) frameworks, powered by large language models (LLMs) or multimodal LLMs (MLLMs), are rapidly maturing as assistants that can perceive context, reason, and act directly within software environments. Among their most…

Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of…

Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…

LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among…

Large Language Models (LLMs) have shown great success as high-level planners for zero-shot game-playing agents. However, these agents are primarily evaluated on Minecraft, where long-term planning is relatively straightforward. In contrast,…

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…

Intelligent agents powered by AI planning assist people in complex scenarios, such as managing teams of semi-autonomous vehicles. However, AI planning models may be incomplete, leading to plans that do not adequately meet the stated…

Significant focus has been placed on integrating large language models (LLMs) with various tools in developing general-purpose agents. This poses a challenge to LLMs' tool-use capabilities. However, there are evident gaps between existing…

Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs. Traditional attack strategies often rely on simplistic heuristics, require access to…

Detecting vulnerabilities in source code remains a critical yet challenging task, especially when benign and vulnerable functions share significant similarities. In this work, we introduce VulTrial, a courtroom-inspired multi-agent…

This study explores the application of chaos engineering to enhance the robustness of Large Language Model-Based Multi-Agent Systems (LLM-MAS) in production-like environments under real-world conditions. LLM-MAS can potentially improve a…

Large language model (LLM)-based agents have emerged as powerful autonomous controllers for digital environments, including mobile interfaces, operating systems, and web browsers. Web navigation, for example, requires handling dynamic…

Large Language Model (LLM) agents are increasingly proposed for autonomous cybersecurity tasks, but their capabilities in realistic offensive settings remain poorly understood. We present DeepRed, an open-source benchmark for evaluating…

A high volume of recent ML security literature focuses on attacks against aligned large language models (LLMs). These attacks may extract private information or coerce the model into producing harmful outputs. In real-world deployments,…

Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and…

Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objective. They measure exploitation effectively, but miss how real Capture-the-Flag (CTF) participants…

As LLM applications grow more complex, developers are increasingly adopting multi-agent architectures to decompose workflows into specialized, collaborative components, introducing structure that constrains agent behavior and exposes useful…

Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…