PulseAugur
实时 14:11:19

新的Voronoi图方法创建鲁棒的对抗性伪装

研究人员开发了一种使用Voronoi图创建对抗性伪装图案的新方法,该方法优化了可打印、结构化图案的种子点位置。与逐像素的对抗性斑块相比,该技术旨在更具视觉可信度和计算效率。在对使用COCO数据集的人员检测进行测试时,该伪装显著降低了检测器的性能,甚至可以通过YOLOv9到YOLOv12等不同检测器家族进行迁移。 AI

影响 这项研究展示了一种新颖的对抗性攻击方法,可能会影响计算机视觉系统的鲁棒性。

排序理由 这是一篇发表在arXiv上的研究论文,详细介绍了一种新颖的对抗性伪装方法。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新的Voronoi图方法创建鲁棒的对抗性伪装

报道来源 [3]

  1. arXiv cs.AI TIER_1 English(EN) · Jens Bayer, Stefan Becker, David M\"unch, Michael Arens, J\"urgen Beyerer ·

    结构化对抗伪装 via Voronoi Diagrams

    arXiv:2606.17711v1 Announce Type: cross Abstract: Pixel-wise adversarial patches are computationally heavy and often visually detectable, limiting utility in security-critical systems. We present adversarial Voronoi camouflage that optimizes only seed-point locations under fixed,…

  2. arXiv cs.CV TIER_1 English(EN) · Shihui Yan, Hu Liu, Junyu Shi, Zihui Zhu, Ziqi Zhou, Yufei Song, Youming Geng, Minghui Li, Shengshan Hu ·

    VFACamou:视图融合对抗性伪装,实现环境自适应物理规避

    arXiv:2606.19736v1 Announce Type: new Abstract: Adversarial camouflage in the physical world remains highly challenging, particularly under UAV reconnaissance where targets undergo continuous geometric changes and extreme illumination variations. Existing methods either optimize …

  3. arXiv cs.CV TIER_1 English(EN) · Jürgen Beyerer ·

    结构化对抗伪装 via Voronoi 图

    Pixel-wise adversarial patches are computationally heavy and often visually detectable, limiting utility in security-critical systems. We present adversarial Voronoi camouflage that optimizes only seed-point locations under fixed, printable palettes using a soft assignment, produ…