AI代理发现先进的大语言模型攻击方法，揭示不单调的安全收益

报道来源 [4]

1. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Tiantian Zhu · 2026-06-04 01:28

   ZERO-APT：一种用于智能防御下的LLM驱动的自动化渗透测试的闭环对抗框架

   LLM-driven automated penetration testing agents are typically evaluated against static targets that neither detect nor respond to attacks, so their behavior under intelligent defense remains untested. The causal consistency of multi-step attack chains likewise hinges on unstable …

2. arXiv cs.AI TIER_1 English(EN) · Alexander Panfilov, Peter Romov, Igor Shilov, Yves-Alexandre de Montjoye, Jonas Geiping, Maksym Andriushchenko · 2026-06-02 04:00

   Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

   arXiv:2603.24511v2 Announce Type: replace-cross Abstract: We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injection evaluations. We deploy frontier agents,…

3. arXiv cs.CL TIER_1 English(EN) · Subhadip Mitra · 2026-06-02 04:00

   Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs

   arXiv:2606.00813v1 Announce Type: cross Abstract: Safety alignment in LLMs does not improve monotonically across model generations. Studying four generations of Google's Gemma family (7B-31B) with quality-diversity evolution (MAP-Elites) as an automated red-teaming probe, we find…

4. arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Subhadip Mitra · 2026-05-30 17:07

   跨代对抗性攻击转移揭示大型语言模型中非单调的安全对齐

   Safety alignment in LLMs does not improve monotonically across model generations. Studying four generations of Google's Gemma family (7B-31B) with quality-diversity evolution (MAP-Elites) as an automated red-teaming probe, we find that Gemma 3 (12B) exhibits 68.7% +/- 5.7% attack…