AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Adversarial Texture for Fooling Person Detectors in the Physical World

Zhanhao Hu, Siyuan Huang, Xiaopei Zhu, Fuchun Sun, Bo Zhang, Xiaolin Hu

CVPR 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Physical adversarial patches and camouflage · 140 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use TC-EGA texture instead of random texturePhysical person-detector attacks · YOLOv2mASR: 0.087 -> 0.743Improved
Use TC-EGA texture instead of random texturePhysical person-detector attacks · YOLOv3mASR: 0.000 -> 0.701Improved
Use TC-EGA texture instead of random texturePhysical person-detector attacks · Faster R-CNNmASR: 0.000 -> 0.930Improved
Use TC-EGA texture instead of random texturePhysical person-detector attacks · Mask R-CNNmASR: 0.000 -> 0.855Improved
Optimize the latent variable after training the expandable generator (ablation)TC-EGA · Inria test set (YOLOv2, digital patch attack)AP: 0.470 -> 0.362Improved
Use a trained FCN generator with toroidal cropping rather than directly optimizing the texture (ablation)TC-EGA · Inria test set (YOLOv2, digital patch attack)AP: 0.664 -> 0.362Improved
Use toroidal cropping instead of random cropping of a fixed-size large patch (ablation)Texture optimization · Inria test set (YOLOv2, digital patch attack)AP: 0.606 -> 0.362Improved
Reduce the fixed optimized patch size from 900×900 to 300×300 (ablation)Random Cropping Attack · Inria test set (YOLOv2, digital patch attack)AP: 0.855 -> 0.606Improved
Tile AdvPatch into a repeated textureAdvPatch · Inria test set (YOLOv2, digital patch attack)AP: 0.352 -> 0.827Hurt
Tile AdvTshirt into a repeated textureAdvTshirt · Inria test set (YOLOv2, digital patch attack)AP: 0.744 -> 0.844Hurt
Apply the texture to a larger dress rather than a T-shirtTC-EGA clothing · Physical YOLOv2 testmASR: 0.771 -> 0.893Improved
Increase camera distance from 1.6 m to 7.0 mTC-EGA T-shirt · Physical YOLOv2 testmASR: 0.791 -> 0.257Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy