TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
Text-to-Video (T2V) models have demonstrated remarkable capability in generating temporally coherent videos from natural language prompts, yet they also risk producing unsafe content such as violence or explicit material. Existing prompt-level defenses are largely inherited from text-to-image safety and operate on the lexical surface of the input, making them vulnerable to jailbreak attacks that disguise harmful intent through rephrasing or adversarial prompting. Moreover, T2V generation introduces a distinctive challenge overlooked by prior work: temporally emergent risk, where a seemingly benign prompt leads to unsafe content through the generator's temporal extrapolation toward narrati...
| Authors | Quanchen Zou, Nizhang Li, Wenxin Zhang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 3 May 2026 |
| Last updated at source | 3 May 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.