Evaluating Multi-Agent Defences Against Jailbreaking Attacks on Large Language Models
On the map: LLM agents and tool use → Agent threats, guardrails and governance
also in 1 more
Abstract (arXiv)
Recent advances in large language models (LLMs) have raised concerns about jailbreaking attacks, i.e., prompts that bypass safety mechanisms. This paper investigates the use of multi-agent LLM systems as a defence against such attacks. We evaluate three jailbreaking strategies, including the original AutoDefense attack and two from Deepleaps: BetterDan and JB. Reproducing the AutoDefense framework, we compare single-agent setups with two- and three-agent configurations. Our results show that multi-agent systems enhance resistance to jailbreaks, especially by reducing false negatives. However, its effectiveness varies by attack type, and it introduces trade-offs such as increased false positives and computational overhead. These findings point to the limitations of current automated defences and suggest directions for improving alignment robustness in future LLM systems.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 10 of its 15 references that are in the map. First posted on arXiv 30 Jun 2025.
Builds on
10 of 15 references.
Closest ancestors · 1
Same direction, newest first
Other references · 9
- 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
- 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
- 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
- 2024How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden Statescited by 98
- 2023Self-Guard: Empower the LLM to Safeguard Itselfcited by 54
- 2024When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Searchcited by 47
- 2024AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Modelscited by 28
- 2024RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Processcited by 11
- 2025Jailbreaking to Jailbreakcited by 9
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem
- 2024Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
- 2025Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations
- 2026SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical Consideration
- 2025MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs
- 2026A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks
- 2025PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
- 2024MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue