Adversarial ML

ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision–Language Models
We propose ReShift, the first aha-moment-driven reasoning-level backdoor framework for Vision–Language Models that redirects chain-of-thought trajectories while preserving surface-level coherence.
Zhihao Dou, Qinjian Zhao, Zhiqiang Gao, Sumon Biswas
Cite