Furina: Fragmented Uncertainty-Driven Refusal Instability Attack 事件

Furina: Fragmented Uncertainty-Driven Refusal Instability Attack arXiv:2605.26158v1 Announce Type: cross Abstract: Safety alignment in large language models (LLMs) and multimodal large language models (MLLMs) is commonly assumed to operate as a near-binary threshold mechanism. We challenge this assumption by revealing that safety behavior is governed by an instability region where small perturbations induce stochastic refusal decisions rather than deterministic outcomes. We develop a multi-metr