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

2026-08-26

AI Summary

本文提出一种自进化多代理框架，通过方法级规则记忆防御LLM越狱攻击，无需参数更新，有效降低攻击成功率并保持良性功能。

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.

Problem

• large language models
• jailbreak attacks
• static defenses
• adaptive strategies
• harmful outputs

Innovation

• self-evolving framework
• cross-interaction rule memory
• method-level rules
• external memory and prompting