ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models

Abstract

Vision--Language Models (VLMs) are increasingly deployed in safety-critical applications, yet remain vulnerable to backdoor attacks. Existing methods primarily manipulate final outputs, often producing reasoning traces that are inconsistent or easily detectable. In this paper, we propose ReShift, the novel aha-moment-driven reasoning-level backdoor framework that explicitly redirects the internal chain-of-thought (CoT) trajectory while preserving surface-level coherence. ReShift introduces a Poi

Categories

Framework mappings

Suggested from the entry's categories.

@misc{dou2026reshift,
  title = {{ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models}},
  author = {Zhihao Dou and Qinjian Zhao and Zhiqiang Gao and Sumon Biswas},
  year = {2026},
  month = jul,
  eprint = {2607.00361},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.00361}
}