English(EN) BadAction: Backdoor Attacks on Interactive Video Generation via Action-Guided Triggers

新的BadAction攻击绕过了交互式视频生成模型的安全性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

研究人员推出了一种名为BadAction的新型后门攻击，专门针对交互式视频生成（IVG）模型。该攻击通过操纵动作序列，诱导模型生成静态的未来帧，使其对用户输入无响应。BadAction使用仅动作和多模态触发器均能实现高成功率，并且重要的是，它能绕过现有的后门检测方法，凸显了IVG系统存在的重大安全漏洞。 AI

影响凸显了交互式视频生成模型中存在的关键安全漏洞，可能影响其部署和可信度。

排序理由该集群包含一篇详细介绍新攻击方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新攻击方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Zhihang Wu, Zhongqi Wang, Jie Zhang, Fengming Gu, Shiguang Shan, Xilin Chen · 2026-10-01 04:00

BadAction：通过动作引导触发器对交互式视频生成进行后门攻击

arXiv:2609.39047v1 Announce Type: new Abstract: Interactive video generation (IVG) models have achieved remarkable progress in producing controllable visual content guided by user-defined actions, yet their security vulnerabilities remain largely unexplored. In this paper, we pre…

本文如何被排名

报道来源 [1]

BadAction：通过动作引导触发器对交互式视频生成进行后门攻击

相关实体

相关话题