Patch Attacks Against Object Detectors Using Out-of-Distribution Smoothing Defenses
Defending Object Detectors against Patch Attacks with Out-of-Distribution Smoothing
Translation in progress — untranslated text is omitted.
The paper proposes the OODSmoother framework to uniformly characterize defense methods aimed at removing adversarial patches, and based on it designs an adaptive attack that can break existing patch defenses and a SemPrior defense that leverages semantic priors. The authors state that SemPrior alone brings up to 40% improvement, and when combined with existing defenses brings up to 60% improvement.
- Object detectors face physically realizable patch attacks; existing defenses mostly rely on training a patch segmenter to detect and remove the patch, and the authors argue that such defenses lack a unified characterization and that ML patch detectors struggle to learn semantic priors.
- The authors propose the OODSmoother framework, which unifies such defenses as an OOD oracle plus an OOD smoother; based on this, they design adaptive attacks that use two losses to attack the patch segmenter and the downstream detector respectively, and propose a SemPrior defense based on color histograms and HSV statistics.
- Under 100×100 patches, the adaptive attack reduces SAC's mAP@IoU=0.5 on COCO from 53.6% to 6.2%, and PatchZero's on VOC from 68.9% to 7.0%; the authors report that SemPrior alone improves by up to 40%, and combined with SAC by up to 60%.
- The authors note that SemPrior may mistakenly affect natural objects using rare colors, and that monochromatic concentrated images are prone to false positives; the experiments cover only gradient attacks and do not consider diffusion-generated attacks; the downstream detector tested is Faster RCNN (R50), with 1000 images evaluated per setting.
Related papers
Both use: Pascal VOC
Both use: CARLA
Both use: MS COCO
Show 3 more papers
Both use: MS COCO
- GeoDetect: Geometric Adversarial Detection for VLPsDefensesarXiv