English(EN) Query-Efficient Video Adversarial Attack with Stylized Logo on Service Computing

新的风格化Logo攻击增强视频对抗性样本

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-17 04:00

研究人员开发了一个新颖的黑盒视频对抗性攻击框架，称为风格化Logo攻击（SLA）。该方法旨在利用深度神经网络（DNN）为视频分类系统生成更自然、更有效的对抗性样本。SLA采用三阶段流程，包括用于Logo的风格参考集、用于优化Logo放置和风格的强化学习，以及用于提高欺骗率的逐步扰动优化。 AI

排序理由该集群包含一篇研究论文，详细介绍了针对视频分类系统的新型对抗性攻击方法。[lever_c_demoted from research: ic=1 ai=1.0]

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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇研究论文，详细介绍了针对视频分类系统的新型对抗性攻击方法。[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: 113 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.CV TIER_1 English(EN) · Duoxun Tang, Yuxin Cao, Xi Xiao, Derui Wang, Sheng Wen, Tianqing Zhu · 2026-06-17 04:00

面向服务计算的查询高效风格化Logo视频对抗性攻击

arXiv:2408.12099v2 Announce Type: replace Abstract: In service computing, video classification has become fundamental to many intelligent applications. While Deep Neural Networks (DNNs) have demonstrated excellent performance in recognizing video content, recent studies have show…