Abstract
Face Recognition Systems that operate in unconstrained environments capture images under varying conditions,such as inconsistent lighting, or diverse face poses. These challenges require including a Face Detection module that regresses bounding boxes and landmark coordinates for proper Face Alignment. This paper shows the effectiveness of Object Generation Attacks on Face Detection, dubbed Face Generation Attacks, and demonstrates for the first time a Landmark Shift Attack that backdoors the coordinate regression task performed by face detectors. We then offer mitigations against these vulnerabilities.
Abstract (translated)
在非约束环境中运行的面部识别系统会在不同条件下捕捉图像，例如光照不一致或不同的面部姿态。这些挑战需要包括一个面部检测模块来回归边界框和地标坐标以实现正确的面部对齐。本文展示了针对面部检测系统的物体生成攻击（称为面部生成攻击）的有效性，并首次演示了一种地标偏移攻击，这种攻击会篡改面部探测器执行的坐标回归任务。最后，我们提供了针对这些漏洞的缓解措施。
URL
https://arxiv.org/abs/2508.00620
