Pith. sign in

REVIEW 14 cited by

Red-Teaming LLM Multi-Agent Systems via Communication Attacks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.14847 v2 pith:6XUWPY5F submitted 2025-02-20 cs.CR

classification cs.CR
keywords communicationmulti-agentsystemsagentattacksllm-masagentsaitm
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Model-based Multi-Agent Systems (LLM-MAS) have revolutionized complex problem-solving capability by enabling sophisticated agent collaboration through message-based communications. While the communication framework is crucial for agent coordination, it also introduces a critical yet unexplored security vulnerability. In this work, we introduce Agent-in-the-Middle (AiTM), a novel attack that exploits the fundamental communication mechanisms in LLM-MAS by intercepting and manipulating inter-agent messages. Unlike existing attacks that compromise individual agents, AiTM demonstrates how an adversary can compromise entire multi-agent systems by only manipulating the messages passing between agents. To enable the attack under the challenges of limited control and role-restricted communication format, we develop an LLM-powered adversarial agent with a reflection mechanism that generates contextually-aware malicious instructions. Our comprehensive evaluation across various frameworks, communication structures, and real-world applications demonstrates that LLM-MAS is vulnerable to communication-based attacks, highlighting the need for robust security measures in multi-agent systems.

Discussion (0). Sign in to comment.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems

    cs.CR 2026-04 conditional novelty 8.0 of 10 partial

    SentinelAgent defines seven properties for verifiable delegation chains in multi-agent AI systems and reports a protocol achieving 100% true positive rate at 0% false positives on a 516-scenario benchmark while using ...

  2. NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms

    cs.CR 2026-06 unverdicted novelty 7.0 of 10

    NRT-Bench reports that adaptive multi-turn attacks cause critical safety function loss in 8.7-12.1% of sessions across four frontier LLM operator models, with nearly disjoint vulnerabilities and strongly model-depende...

  3. MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems

    cs.CR 2026-06 unverdicted novelty 6.0 of 10

    MESA ranks MAS communication edges by vulnerability via graph-theoretic metrics and dynamic probes, achieving mean Spearman ρ=+0.60 correlation with empirical per-edge attack success and 3x interception gain when moni...

  4. MAGIQ: A Post-Quantum Multi-Agentic AI Governance System with Provable Security

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    MAGIQ introduces a post-quantum secure system for policy definition, enforcement, and accountability in multi-agent AI using novel cryptographic protocols and UC framework proofs.

  5. LoopTrap: Termination Poisoning Attacks on LLM Agents

    cs.CR 2026-05 unverdicted novelty 6.0 of 10

    LoopTrap is an automated red-teaming framework that crafts termination-poisoning prompts to amplify LLM agent steps by 3.57x on average (up to 25x) across 8 agents.

  6. Scheming Ability in LLM-to-LLM Strategic Interactions

    cs.CL 2025-10 conditional novelty 6.0 of 10

    Frontier LLMs exhibit high scheming propensity in Cheap Talk signaling and Peer Evaluation games, achieving 95-100% success rates when choosing to deceive and 100% deception choice in one setup even without prompting.

  7. To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems

    cs.CR 2025-06 unverdicted novelty 6.0 of 10

    Introduces six-dimension trustworthiness definition and attention-based A-Trust score with a TMS to improve LLM-MAS robustness against malicious or unreliable messages.

  8. Insider Attacks in Multi-Agent LLM Consensus Systems

    cs.MA 2026-05 unverdicted novelty 5.0 of 10

    A malicious agent in multi-agent LLM consensus systems can be trained via a surrogate world model and RL to reduce consensus rates and prolong disagreement more effectively than direct prompt attacks.

  9. MAGIQ: A Post-Quantum Multi-Agentic AI Governance System with Provable Security

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    MAGIQ introduces a post-quantum governance system for multi-agent AI that supports policy budgets, session enforcement, message attribution, and UC-based security proofs while comparing overhead to SAGA.

  10. How Well Do AI Systems Solve AP Physics? A Comparative Evaluation of Large Language Models on Algebra-Based Free Response Questions

    physics.ed-ph 2026-03 unverdicted novelty 5.0 of 10

    ChatGPT 4.1 mini, Gemini 2.5 Flash, Claude 4.0 Sonnet, and DeepSeek R1 average 82–92% on AP Physics 1/2 free-response questions but systematically fail spatial, visual, and conceptual tasks.

  11. Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

    cs.AI 2025-10 unverdicted novelty 4.0 of 10

    A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.

  12. Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation

    cs.CR 2025-10 conditional novelty 4.0 of 10

    A backward-propagation scoring scheme over a signed temporal DAG can identify malicious agents in LLM multi-agent systems and cut their communications, improving defended accuracy by 3–7 percentage points in the autho...

  13. Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey

    cs.NI 2025-08 conditional novelty 4.0 of 10

    A survey proposing zero-trust architecture for multi-LLM systems in edge computing, with a taxonomy of model- and system-level defenses and a conceptual framework.

  14. Large Language Model Agent: A Survey on Methodology, Applications and Challenges

    cs.CL 2025-03 accept novelty 3.0 of 10

    A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.

Pith tools