A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks
[Kryptografia i bezpieczeństwo] Autorzy: Tongyan Hu, Bryan Hooi
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 …
- Kategoria arxiv
- cs.CR
- Kategoria
- Kryptografia i bezpieczeństwo