# Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate

arXiv: https://arxiv.org/abs/2504.16489 · HTML: https://mlsanity.com/paper/2504.16489/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 45 of its 48 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 45)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks](https://mlsanity.com/paper/2302.05733/) (2023)
- [Jailbreak Attacks and Defenses Against Large Language Models: A Survey](https://mlsanity.com/paper/2407.04295/) (2024)
- [Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation](https://mlsanity.com/paper/2311.03348/) (2023)
- [Automatically Auditing Large Language Models via Discrete Optimization](https://mlsanity.com/paper/2303.04381/) (2023)
- [Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast](https://mlsanity.com/paper/2402.08567/) (2024)
- [Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems](https://mlsanity.com/paper/2410.07283/) (2024)
- [The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies](https://mlsanity.com/paper/2407.19354/) (2024)
- [On Prompt-Driven Safeguarding for Large Language Models](https://mlsanity.com/paper/2401.18018/) (2024)
- [Improving Multi-Agent Debate with Sparse Communication Topology](https://mlsanity.com/paper/2406.11776/) (2024)
- [How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States](https://mlsanity.com/paper/2406.05644/) (2024)
- [GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis](https://mlsanity.com/paper/2402.13494/) (2024)
- [Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence](https://mlsanity.com/paper/2407.07061/) (2024)
- [Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities](https://mlsanity.com/paper/2407.07791/) (2024)
- [Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication](https://mlsanity.com/paper/2312.01823/) (2023)

## Built on by (most cited first, 10 of 10)

- [Free-MAD: Consensus-Free Multi-Agent Debate](https://mlsanity.com/paper/2509.11035/) (2025)
- [A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?](https://mlsanity.com/paper/2505.10924/) (2025)
- [MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems](https://mlsanity.com/paper/2507.13038/) (2025)
- [From Logic Monopoly to Social Contract: Separation of Power and the Institutional Foundations for Autonomous Agent Economies](https://mlsanity.com/paper/2603.25100/) (2026)
- [Architecture Matters for Multi-Agent Security](https://mlsanity.com/paper/2604.23459/) (2026)
- [SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models](https://mlsanity.com/paper/2506.18543/) (2025)
- [SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems](https://mlsanity.com/paper/2609.00595/) (2026)
- [Governance by Design: A Parsonian Institutional Architecture for Internet-Wide Agent Societies](https://mlsanity.com/paper/2604.11337/) (2026)
- [Agent-Native Immune System: Architecture, Taxonomy, and Engineering](https://mlsanity.com/paper/2606.28270/) (2026)
- [Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives](https://mlsanity.com/paper/2609.16694/) (2026)

## Abstract (arXiv)

Multi-Agent Debate (MAD), leveraging collaborative interactions among Large Language Models (LLMs), aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing characteristics, particularly susceptibility to jailbreak attacks eliciting harmful content, remain critically underexplored. This paper systematically investigates the jailbreak vulnerabilities of four prominent MAD frameworks built upon leading commercial LLMs (GPT-4o, GPT-4, GPT-3.5-turbo, and DeepSeek) without compromising internal agents. We introduce a novel structured prompt-rewriting framework specifically designed to exploit MAD dynamics via narrative encapsulation, role-driven escalation, iterative refinement, and rhetorical obfuscation. Our extensive experiments demonstrate that MAD systems are inherently more vulnerable than single-agent setups. Crucially, our proposed attack methodology significantly amplifies this fragility, increasing average harmfulness from 28.14% to 80.34% and achieving attack success rates as high as 80% in certain scenarios. These findings reveal intrinsic vulnerabilities in MAD architectures and underscore the urgent need for robust, specialized defenses prior to real-world deployment.