Across model-harness combinations, agents with comparable competence exhibit markedly different safety outcomes, showing that task capability alone does not guarantee safe execution, and highlighting the need to move beyond risk recognition toward enforcing safety throughout execution.
Wei-Tao Feng, Heng-Heng Xiong, Zi-Hao Zeng et al.· 0 citations
This work proposes AEGIS (Adaptive Evasion Guard via Identification and Steering), an inference-time defense that applies similarity-aware repulsion only at the identified vulnerable heads of VSA and preserves benign fidelity, avoids suppressing hard-negative concepts, and transfers to SD 2.1 and FLUX.
Yuanmin Huang, Zhenfei Zhang, Mi Zhang et al.· arXiv.org· 0 citations
Oyster-II is proposed, a reinforcement learning (RL)-based constructive safety alignment framework that adopts a Zero-RL paradigm combined with a multi-stage reinforcement learning strategy that comprehensively surpasses both Qwen3-14B and its predecessor Oyster-I on safety dimensions.
Jiyang Guan, Yong Xie, Jun Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.