AI Paper Atlas

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

Deformable and Multi-view Gradient-Aligned Physical Adversarial Camouflage

Jiawei Liang, Puning Zhao, tianrui lou, Haoqing Zhang, Xianghao Jiao, Bozheng Lin, Ming Zhang, Xiaochun Cao

ECCV 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Physical adversarial patches and camouflage · 0 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 Deformable Texture Field (DTF) parameterization (ablation)adversarial camouflage · YOLOv3 0 degAP@0.5 (%): 61.70 -> 33.06Improved
add Gradient-Aligned Meta-Optimization (GAMO) (ablation)adversarial camouflage · YOLOv3 0 degAP@0.5 (%): 61.70 -> 40.13Improved
combine DTF and GAMO (ablation)adversarial camouflage · YOLOv3 0 degAP@0.5 (%): 33.06 -> 19.05Improved
combine DTF and GAMO (ablation)adversarial camouflage · Faster R-CNN 0 deg (black-box)AP@0.5 (%): 85.17 -> 42.92Improved
use GAMO instead of PCGrad for gradient conflicts (ablation)DTF · Gradient-conflict handlingAP@0.5 (%): 20.25 -> 7.68Improved
use GAMO instead of GRAC for gradient conflicts (ablation)DTF · Gradient-conflict handlingAP@0.5 (%): 12.34 -> 7.68Improved
add GAMO to DTF (ablation)DTF · Gradient cosine similaritygradient cosine similarity: 0.0048 -> 0.0070Improved
proposed method vs GRAC on GLIPOurs · GLIP transferAP@0.5 (%): 41.42 -> 43.72Hurt
proposed method vs GRAC on DINOOurs · DINO transferAP@0.5 (%): 23.03 -> 13.36Improved
proposed method vs GRAC on physical Faster R-CNN 20 degOurs · Physical 1:24 carAP@0.5 (%): 54.30 -> 41.15Improved
proposed method vs GRAC per-view costOurs · Efficiency per viewlatency (ms): 430.10 -> 135.17Improved

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