AI Paper Atlas

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

Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling

Xiaopei Zhu, Siyuan Huang, Zhanhao Hu, Jianmin Li, Jun Zhu, Xiaolin Hu

TPAMI 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
optimize black-patch layout instead of random placement3D infrared clothing · FLIR_ADAS_1_3 digitalASR: 38.19% -> 86.38%Improved
optimize layout instead of random placement on physical clothing (indoor)aerogel clothing · Physical, indoorASR: 26.53% -> 80.11%Improved
optimize layout instead of random placement on physical clothing (outdoor)aerogel clothing · Physical, outdoorASR: 23.03% -> 76.85%Improved
increase number of patches from 6 to 36 (ablation)3D infrared clothing · FLIR_ADAS_1_3 digitalASR: 22.38% -> 86.38%Improved
increase number of patches from 36 to 60 (ablation)3D infrared clothing · FLIR_ADAS_1_3 digitalASR: 86.38% -> 83.73%Hurt
increase patch size from 2 cm to 6 cm (ablation)3D infrared clothing · FLIR_ADAS_1_3 digitalASR: 51.30% -> 86.38%Improved
increase patch size from 6 cm to 12 cm (ablation)3D infrared clothing · FLIR_ADAS_1_3 digitalASR: 86.38% -> 78.12%Hurt
add distance loss L_dist (lambda 0 -> 0.1) (ablation)3D infrared clothing · FLIR_ADAS_1_3 digitalASR: 72.66% -> 86.38%Improved
raise lambda from 0.1 to 1 (ablation)3D infrared clothing · FLIR_ADAS_1_3 digitalASR: 86.38% -> 76.61%Hurt
optimize against an ensemble of detectors instead of YOLOv9 only (ablation)3D infrared clothing · Transfer to DETR, digitalASR: 29.75% -> 81.03%Improved
optimize against an ensemble of detectors instead of YOLOv9 only (ablation)3D infrared clothing · Transfer to YOLOv8, digitalASR: 58.36% -> 80.28%Improved
optimize against an ensemble of detectors instead of YOLOv9 only (ablation)aerogel clothing · Transfer to DETR, physicalASR: 21.69% -> 70.05%Improved

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