Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models

Abstract

Recently, text-to-video (T2V) models have been widely deployed, sparking growing concerns over their robustness against jailbreak attacks. Existing jailbreak methods, mostly adapted from text-to-image attacks, suffer notable drawbacks when applied to T2V systems. They fail to fully leverage temporal consistency, an inherent characteristic of video generation. Besides, these methods demand heavy video query optimization, which is infeasible in practical black-box scenarios. Their adversarial prom

Categories

Framework mappings

Suggested from the entry's categories.

@misc{peng2026between,
  title = {{Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models}},
  author = {Xingkai Peng and Jun Jiang and Jiayang Liu and Kejiang Chen and Weiming Zhang},
  year = {2026},
  month = jul,
  eprint = {2607.17279},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.17279}
}