cs.CRNov 18, 2026

Attacks and Defenses in Decentralized Multi-Agent Systems with Hop-by-Hop Task Decomposition and Delegation

Authors: Matthew D. Laws, Maria Lazou, Alina Oprea, Cristina Nita-Rotaru

Organizations: Northeastern University

Abstract

Decentralized multi-agent LLM systems enable independently administered agents, each with its own operator, model, memory, and configuration, to collaborate on complex tasks without centralized coordination. Agents autonomously decompose tasks, execute subtasks and delegate remaining work to peers, enabling scalability and eliminating single points of failure. However, decentralization also introduces significant security challenges, as no single entity has complete visibility into task execution or the authority to enforce correct behavior across agents. In this paper, we systematize threats from malicious agents in decentralized multi-agent systems and propose mitigation techniques. We first design and evaluate attacks against integrity, availability, and confidentiality, demonstrating that a single malicious agent can cause up to 100% task failure, inflate token consumption and runtime by up to 7.7x and 3.2x, respectively, and exfiltrate up to 94% of relevant prior tasks from benign agents. We then present a cryptographic protocol that produces an irrefutable verified execution trace of every action taken in the system and develop an auditor that analyzes these traces to detect and attribute malicious behavior. Evaluations on HiddenBench using gpt-6.1-sol and Qwen3.8-27B-FP8 show that our protocol incurs negligible latency overhead, while the auditor detects and correctly attributes 98% of attacks, including those that comply with the protocol.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Cryptographically Secure Agent-to-Agent Communication in Multi-Agent Systems

    Oct 16, 2026Karol Budzyn, Adrian Brodzik, Mateusz SzczepkowskiMulti-Agent System SecurityMulti-Agent Communication

  2. Securing Multi-Agent Systems by Design

    Nov 13, 2026Xilong Wang, Xiaoxing Chen, Neil GongMulti-Agent System SecurityMulti-Agent Systems

  3. Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study

    Jul 27, 2026Diego Fernandez Arias, Dev Prashant Mistry, Ren Wang +1Multi-Agent LLM SystemsLLM Backdoor Attacks