TEAR：面向文本到视频模型的时序感知自动化红队测试
TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models
AI总结：
TEAR通过时序感知自动化红队测试框架，有效识别文本到视频模型中的安全风险，实验显示攻击成功率高达80%
摘要：
文本到视频（T2V）模型能够合成高质量且时间上连贯的动态视频内容，但其多样的生成也 inherently 引入了关键的安全挑战。现有安全评估方法，专注于静态图像和文本生成，无法捕捉视频生成中的复杂时间动态。为此，我们提出了一种名为TEAR的时序感知自动化红队框架，该框架旨在揭示与T2V模型动态时间序列相关的安全风险。TEAR采用一个通过两阶段方法优化的时序感知测试生成器：初始生成器训练和时序感知在线偏好学习，以创建文本上无害的提示，利用时间动态来引发违反政策的视频输出。并采用一个精炼模型，周期性地提高提示的隐蔽性和对抗有效性。广泛的实验评估证明了TEAR在开源和商业T2V系统中的有效性，攻击成功率超过80%，显著优于先前最佳结果的57%。
英文摘要：
Text-to-Video (T2V) models are capable of synthesizing high-quality, temporally coherent dynamic video content, but the diverse generation also inherently introduces critical safety challenges. Existing safety evaluation methods,which focus on static image and text generation, are insufficient to capture the complex temporal dynamics in video generation. To address this, we propose a TEmporal-aware Automated Red-teaming framework, named TEAR, an automated framework designed to uncover safety risks specifically linked to the dynamic temporal sequencing of T2V models. TEAR employs a temporal-aware test generator optimized via a two-stage approach: initial generator training and temporal-aware online preference learning, to craft textually innocuous prompts that exploit temporal dynamics to elicit policy-violating video output. And a refine model is adopted to improve the prompt stealthiness and adversarial effectiveness cyclically. Extensive experimental evaluation demonstrates the effectiveness of TEAR across open-source and commercial T2V systems with over 80% attack success rate, a significant boost from prior best result of 57%.
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。
