AI Paper Atlas

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

Gradient-Reweighted Adversarial Camouflage for Physical Object Detection Evasion

Jiawei Liang, Siyuan Liang, Tianrui Lou, Ming Zhang, Wenjin Li, Dunqiu Fan, Xiaochun Cao

ICCV 2025 · Adversarial robustness and security › Attacks on text and graphs · approach: Physical adversarial patches and camouflage · 1 citations (OpenAlex)

Read the paperCheck 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
add gradient reweighting (ablation)GRAC baseline texture optimization · YOLOv3 white-boxAP@0.5: 19.02 -> 15.56Improved
add illumination simulation (ablation)GRAC baseline · YOLOv3 white-boxAP@0.5: 19.02 -> 16.48Improved
add texture regularization (pooling) (ablation)GRAC baseline · YOLOv3 white-boxAP@0.5: 19.02 -> 11.86Improved
add all three components (ablation)GRAC baseline · YOLOv3 white-boxAP@0.5: 19.02 -> 2.94Improved
add gradient reweighting (ablation)GRAC baseline · Faster R-CNN black-boxAP@0.5: 35.14 -> 26.85Improved
add illumination simulation (ablation)GRAC baseline · Faster R-CNN black-boxAP@0.5: 35.14 -> 30.39Improved
add texture regularization (ablation)GRAC baseline · Faster R-CNN black-boxAP@0.5: 35.14 -> 28.18Improved
add all three components (ablation)GRAC baseline · PVT black-boxAP@0.5: 23.39 -> 18.03Improved
replace best prior method RAUCA with GRACadversarial camouflage · YOLOv3 elevation averageAP@0.5: 16.31 -> 2.94Improved
replace RAUCA with GRAC on black-box detectorsadversarial camouflage · Mask R-CNNAP@0.5: 28.90 -> 29.31No clear effect
increase gradient accumulation steps (ablation)gradient reweighting · YOLOv3 white-box vs black-boxAP@0.5Mixed
increase texture pooling size (ablation)texture regularization · pooling-size sweepAP@0.5Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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