AI Paper Atlas

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

Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems

Jiahuan Long, Tingsong Jiang, Hanqing Liu, Chao Ma, Weien Zhou, Yang Yang, Wen Yao

CVPR 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
use optimized polygonal dual-modal patch instead of AdvYOLO patchvisible detectors · INRIA YOLOv3ASR (%): 34.6 -> 54.4Improved
use optimized polygonal dual-modal patch instead of AdvYOLO patchvisible detectors · INRIA DETRASR (%): 25.2 -> 38.4Improved
use optimized polygonal dual-modal patch instead of AdvIBinfrared detectors · LLVIP YOLOv5ASR (%): 75.1 -> 88.6Improved
use optimized polygonal dual-modal patch instead of AdvIBinfrared detectors · LLVIP DETRASR (%): 65.8 -> 80.2Improved
heat clothing to activate hidden patch (30 s start, 50 s full) (ablation)adversarial clothing · physical testactivation time: 50 sImproved
increase distance beyond 30 m (ablation)adversarial clothing RGB patch · physical testvisible-spectrum evasionHurt
increase viewing angle up to 35 degrees (ablation)adversarial clothing · physical testdual-modal evasionNo clear effect

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