arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.07028cs.CRcs.CV
收藏

两个框架至关重要:一种针对文本到视频模型劫持的时序攻击

Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking

College of Science, Mathematics and Technology, Wenzhou-Kean University(科学、数学与技术学院,温州市凯恩大学);State Key Laboratory of Complex & Critical Software Environment, Beihang University(复杂与关键软件环境国家重点实验室,北航);AI Security Lab(360人工智能安全实验室)

Moyang Chen, Zonghao Ying, Wenzhuo Xu, Quancheng Zou, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang

AI总结:

本文提出TFM攻击方法,通过碎片化提示和隐式替换,提高文本到视频模型的劫持效果,显著提升攻击成功率。

摘要:

最近的文本到视频(T2V)模型能够从轻量级的自然语言提示中合成复杂的视频,这在现实世界中滥用时引发了紧迫的安全对齐问题。先前的劫持攻击通常将不安全的提示改写成 paraphrases,以逃避内容过滤同时保持意义。然而,这些方法往往仍然保留了显式的敏感提示,在输入文本中,因此忽略了更深层次、视频特定的弱点。在本文中,我们识别了在碎片化提示下T2V系统中的时序轨迹填充漏洞:当提示仅指定稀疏的边界条件(例如起始和结束帧)并留下中间演变未指定时,模型可能会自主重建一个合理的轨迹,其中包括有害的中间帧,尽管提示看起来对输入或输出侧过滤是无害的。基于这一观察,我们提出了TFM。这种碎片化提示框架将原本不安全的请求转换为一个时间稀疏的两帧提取,并通过隐式替换进一步减少显性敏感提示。在多个开源和商业T2V模型上的广泛评估表明,TFM在多个开源和商业T2V模型上广泛评估表明,TFM一致地增强了劫持效果,实现了在商业系统上的攻击成功率增加高达12%。我们的发现强调了需要考虑模型驱动完成的时序意识安全机制的必要性,而不仅仅是提示表层形式。

英文摘要:

Recent text-to-video (T2V) models can synthesize complex videos from lightweight natural language prompts, raising urgent concerns about safety alignment in the event of misuse in the real world. Prior jailbreak attacks typically rewrite unsafe prompts into paraphrases that evade content filters while preserving meaning. Yet, these approaches often still retain explicit sensitive cues in the input text and therefore overlook a more profound, video-specific weakness. In this paper, we identify a temporal trajectory infilling vulnerability of T2V systems under fragmented prompts: when the prompt specifies only sparse boundary conditions (e.g., start and end frames) and leaves the intermediate evolution underspecified, the model may autonomously reconstruct a plausible trajectory that includes harmful intermediate frames, despite the prompt appearing benign to input or output side filtering. Building on this observation, we propose TFM. This fragmented prompting framework converts an originally unsafe request into a temporally sparse two-frame extraction and further reduces overtly sensitive cues via implicit substitution. Extensive evaluations across multiple open-source and commercial T2V models demonstrate that TFM consistently enhances jailbreak effectiveness, achieving up to a 12% increase in attack success rate on commercial systems. Our findings highlight the need for temporally aware safety mechanisms that account for model-driven completion beyond prompt surface form.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑