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

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 that Gemma 3 (12B) exhibits 68.7% +/- 5.7% attack success rate (ASR; mean +/- std, 3 seeds), significantly higher than i