On the Resilience of Multi-Agent Systems with Malicious Agents

• URL: http://arxiv.org/abs/2408.00989v2
• Date: Mon, 30 Sep 2024 17:38:26 GMT
• Title: On the Resilience of Multi-Agent Systems with Malicious Agents
• Authors: Jen-tse Huang, Jiaxu Zhou, Tailin Jin, Xuhui Zhou, Zixi Chen, Wenxuan Wang, Youliang Yuan, Maarten Sap, Michael R. Lyu,
• Abstract summary: This paper investigates what is the resilience of multi-agent system structures under malicious agents. We devise two methods, AutoTransform and AutoInject, to transform any agent into a malicious one. We show that two defense methods, introducing a mechanism for each agent to challenge others' outputs, or an additional agent to review and correct messages, can enhance system resilience.
• Score: 58.79302663733702
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-agent systems, powered by large language models, have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, when agents are deployed separately, there is a risk that malicious users may introduce malicious agents who generate incorrect or irrelevant results that are too stealthy to be identified by other non-specialized agents. Therefore, this paper investigates two essential questions: (1) What is the resilience of various multi-agent system structures (e.g., A$\rightarrow$B$\rightarrow$C, A$\leftrightarrow$B$\leftrightarrow$C) under malicious agents, on different downstream tasks? (2) How can we increase system resilience to defend against malicious agents? To simulate malicious agents, we devise two methods, AutoTransform and AutoInject, to transform any agent into a malicious one while preserving its functional integrity. We run comprehensive experiments on four downstream multi-agent systems tasks, namely code generation, math problems, translation, and text evaluation. Results suggest that the "hierarchical" multi-agent structure, i.e., A$\rightarrow$(B$\leftrightarrow$C), exhibits superior resilience with the lowest performance drop of $23.6\%$, compared to $46.4\%$ and $49.8\%$ of other two structures. Additionally, we show the promise of improving multi-agent system resilience by demonstrating that two defense methods, introducing a mechanism for each agent to challenge others' outputs, or an additional agent to review and correct messages, can enhance system resilience. Our code and data are available at https://github.com/CUHK-ARISE/MAS-Resilience.

Related papers

• Multi-Agent Stochastic Bandits Robust to Adversarial Corruptions [6.234292942334148]
  We propose a multi-agent cooperative learning algorithm that is robust to adversarial corruptions. As a side-product, our algorithm also improves the state-of-the-art regret bounds when reducing to both the single-agent and homogeneous multi-agent scenarios.
  arXiv  Detail & Related papers  (2024-11-12T20:20:26Z)
• Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks [39.084974125007165]
  We introduce Magentic-One, a high-performing open-source agentic system for solving complex tasks. Magentic-One uses a multi-agent architecture where a lead agent, the Orchestrator, tracks progress, and re-plans to recover from errors. We show that Magentic-One achieves statistically competitive performance to the state-of-the-art on three diverse and challenging agentic benchmarks.
  arXiv  Detail & Related papers  (2024-11-07T06:36:19Z)
• A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns [19.015202590038996]
  A key component of agents is memory, which stores vital information but is susceptible to jailbreak attacks. Existing research mainly focuses on single-agent attacks and shared memory attacks. We propose the Troublemaker Makes Chaos in Honest Town (TMCHT) task, a large-scale, multi-agent, multi-topology text-based attack evaluation framework.
  arXiv  Detail & Related papers  (2024-10-21T16:21:24Z)
• Agent-as-a-Judge: Evaluate Agents with Agents [61.33974108405561]
  We introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We present DevAI, a new benchmark of 55 realistic automated AI development tasks.
  arXiv  Detail & Related papers  (2024-10-14T17:57:02Z)
• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments [116.97648507802926]
  Large language models (LLMs) are considered a promising foundation to build such agents. We take the first step towards building generally-capable LLM-based agents with self-evolution ability. We propose AgentGym, a new framework featuring a variety of environments and tasks for broad, real-time, uni-format, and concurrent agent exploration.
  arXiv  Detail & Related papers  (2024-06-06T15:15:41Z)
• A Unified Debugging Approach via LLM-Based Multi-Agent Synergy [39.11825182386288]
  FixAgent is an end-to-end framework for unified debug through multi-agent synergy. It significantly outperforms state-of-the-art repair methods, fixing 1.25$times$ to 2.56$times$ bugs on the repo-level benchmark, Defects4J.
  arXiv  Detail & Related papers  (2024-04-26T04:55:35Z)
• Malicious Agent Detection for Robust Multi-Agent Collaborative Perception [52.261231738242266]
  Multi-agent collaborative (MAC) perception is more vulnerable to adversarial attacks than single-agent perception. We propose Malicious Agent Detection (MADE), a reactive defense specific to MAC perception. We conduct comprehensive evaluations on a benchmark 3D dataset V2X-sim and a real-road dataset DAIR-V2X.
  arXiv  Detail & Related papers  (2023-10-18T11:36:42Z)
• MADiff: Offline Multi-agent Learning with Diffusion Models [79.18130544233794]
  Diffusion model (DM) recently achieved huge success in various scenarios including offline reinforcement learning. We propose MADiff, a novel generative multi-agent learning framework to tackle this problem. Our experiments show the superior performance of MADiff compared to baseline algorithms in a wide range of multi-agent learning tasks.
  arXiv  Detail & Related papers  (2023-05-27T02:14:09Z)
• ERMAS: Becoming Robust to Reward Function Sim-to-Real Gaps in Multi-Agent Simulations [110.72725220033983]
  Epsilon-Robust Multi-Agent Simulation (ERMAS) is a framework for learning AI policies that are robust to such multiagent sim-to-real gaps. ERMAS learns tax policies that are robust to changes in agent risk aversion, improving social welfare by up to 15% in complextemporal simulations. In particular, ERMAS learns tax policies that are robust to changes in agent risk aversion, improving social welfare by up to 15% in complextemporal simulations.
  arXiv  Detail & Related papers  (2021-06-10T04:32:20Z)
• Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical Systems [3.9599054392856488]
  quadratic analysis is challenging in Multi-Agent Reinforcement Learning (MARL) We propose a MARL algorithm based on the construction of an auxiliary single-agent LQ problem. We show that our algorithm provides a $tildeO(sqrtT)$ regret bound.
  arXiv  Detail & Related papers  (2020-01-27T23:37:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.