Conference
Open access
2026
Mitigating Safety Context Amnesia in Multimodal Reasoning Models via Intent-Guided Safety Reasoning
Intent-Guided Safety Reasoning (IGSR), an inference-time defense that operates without modifying target model parameters, is proposed, which improves defense success rates by over 62% compared to baselines, while largely preserving task utility.
Xiyao Dong, Guangsheng Cheng, Yilong Chen et al.
· Annual Meeting of the Associ... · 0 citations