Score: 1

Benchmarking Adversarial Patch Selection and Location

Published: August 3, 2025 | arXiv ID: 2508.01676v1

By: Shai Kimhi, Avi Mendlson, Moshe Kimhi

Potential Business Impact:

Makes computer vision models easily fooled.

Adversarial patch attacks threaten the reliability of modern vision models. We present PatchMap, the first spatially exhaustive benchmark of patch placement, built by evaluating over 1.5e8 forward passes on ImageNet validation images. PatchMap reveals systematic hot-spots where small patches (as little as 2% of the image) induce confident misclassifications and large drops in model confidence. To demonstrate its utility, we propose a simple segmentation guided placement heuristic that leverages off the shelf masks to identify vulnerable regions without any gradient queries. Across five architectures-including adversarially trained ResNet50, our method boosts attack success rates by 8 to 13 percentage points compared to random or fixed placements. We publicly release PatchMap and the code implementation. The full PatchMap bench (6.5B predictions, multiple backbones) will be released soon to further accelerate research on location-aware defenses and adaptive attacks.

Country of Origin
🇮🇱 Israel

Repos / Data Links

Page Count
9 pages

Category
Computer Science:
CV and Pattern Recognition