A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks

• URL: http://arxiv.org/abs/2608.26008v1
• Date: Wed, 26 Aug 2026 16:52:06 GMT
• Title: A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks
• Abstract summary: Large language models (LLMs) remain vulnerable to jailbreak attacks.<n>We propose a self-evolving test-time defense built around a persistent, cross-interaction rule memory.
• Score: 53.12252890906191
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) remain vulnerable to jailbreak attacks that exploit techniques such as role-playing, obfuscation, code transformation, and multi-step indirection to elicit harmful outputs. As jailbreak strategies keep emerging, defenses have proliferated in an ongoing cat-and-mouse game, yet most remain static: their safety behavior is fixed at deployment, so they cannot accumulate defensive experience or adapt to unseen strategies. We propose a self-evolving test-time defense built around a persistent, cross-interaction rule memory: when an attack succeeds, the framework abstracts that failure into a method-level rule capturing the structural attack wrapper rather than the harmful topic, and reuses it against future inputs. Because rules are method-level, one induced rule generalizes across an entire attack family, and the label space expands as novel wrappers appear. The mechanism operates entirely through external memory and prompting, with no parameter updates, and applies to both open-weight and black-box API models. We realize it as four cooperating modules, but the contribution is the memory-based adaptation mechanism, not the module decomposition. Across four black-box jailbreak families and multiple models, our method substantially reduces attack success rates while preserving benign utility, remains robust under an adaptive composite-wrapper attack, and does not increase over-refusal as the memory grows.

Related papers

• Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies [62.65225104423404]
  Self-evolving agent systems introduce a qualitatively new threat landscape in which adversarial influences become permanently encoded.<n>We present a systematic security and privacy analysis organized around the Module-Lifecycle Attack Surface matrix.<n>Our findings establish that self-evolution converts every known attack category from session-bounded to lineage-persistent.
  arXiv  Detail & Related papers  (2026-06-22T09:23:50Z)
• SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking [24.752522468137443]
  We propose a Self-Evolving Rule-Driven Training-Free Jailbreak (SRTJ) framework that systematically discovers, composes, and refines attack strategies.<n>The resulting rule memory evolves in a hierarchical multi-level manner, explicitly organizing distilled attack knowledge into long-term, middle-term, and short-term rules.<n>SRTJ achieves strong and stable attack performance across different target LLMs, while exhibiting improved generalization and robustness compared to existing jailbreak methods.
  arXiv  Detail & Related papers  (2026-05-01T17:27:45Z)
• Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense [55.77152277982117]
  We introduce Layer-AdvPatcher, a methodology designed to defend against jailbreak attacks.<n>We use an unlearning strategy to patch specific layers within large language models through self-augmented datasets.<n>Our framework reduces the harmfulness and attack success rate of jailbreak attacks.
  arXiv  Detail & Related papers  (2025-01-05T19:06:03Z)
• Jailbreaking? One Step Is Enough! [6.142918017301964]
  Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs.<n>We propose a Reverse Embedded Defense Attack (REDA) mechanism that disguises the attack intention as the "defense" intention.<n>To enhance the model's confidence and guidance in "defensive" intentions, we adopt in-context learning (ICL) with a small number of attack examples.
  arXiv  Detail & Related papers  (2024-12-17T07:33:41Z)
• SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner [21.414701448926614]
  This paper introduces a generic LLM jailbreak defense framework called SelfDefend.<n>We empirically validate using mainstream GPT-3.5/4 models against major jailbreak attacks.<n>To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models.
  arXiv  Detail & Related papers  (2024-06-08T15:45:31Z)
• AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens [83.08119913279488]
  We present a systematic analysis of the dependency relationships in jailbreak attack and defense techniques. We propose three comprehensive, automated, and logical frameworks. We show that the proposed ensemble jailbreak attack and defense framework significantly outperforms existing research.
  arXiv  Detail & Related papers  (2024-06-06T07:24:41Z)
• AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting [54.931241667414184]
  We propose textbfAdaptive textbfShield Prompting, which prepends inputs with defense prompts to defend MLLMs against structure-based jailbreak attacks. Our methods can consistently improve MLLMs' robustness against structure-based jailbreak attacks.
  arXiv  Detail & Related papers  (2024-03-14T15:57:13Z)
• Weak-to-Strong Jailbreaking on Large Language Models [92.52448762164926]
  Large language models (LLMs) are vulnerable to jailbreak attacks.<n>Existing jailbreaking methods are computationally costly.<n>We propose the weak-to-strong jailbreaking attack.
  arXiv  Detail & Related papers  (2024-01-30T18:48:37Z)

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.