DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Models

ArXi:2509.04597v2 Announce Type: replace Object detection is fundamental to various real-world applications, such as security monitoring and surveillance video analysis. Despite their advancements, state-of-the-art object detectors are still vulnerable to adversarial patch attacks, which can be easily applied to real-world objects to either conceal actual items or create non-existent ones, leading to severe consequences. In this work, we