AI Paper Atlas

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

AntiStyler: Defending Object Detection Models Against Adversarial Patch Attacks Using Style Removal

Idan Yankelev, Edita Grolman, Yarin Yerushalmi Levi, Amit Giloni, Omer Hofman, Toshiya Shimizu, Yuval Elovici, Asaf Shabtai

CVPR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Physical adversarial patches and camouflage

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
remove random padding (ablation)AntiStyler · COCO, Google patch (benign images)mAP@0.5: 51.6 -> 38.8Hurt
add random-value padding (ablation)AntiStyler · COCO, M-PGD patch (adversarial images)mAP@0.5: 35.7 -> 38.0Improved
add filter, enhancement and mask phases (ablation)AntiStyler · COCO, Google patch (adversarial images)mAP@0.5: 29.3 -> 32.5Improved
add enhancement phase (spatial filters) to raw mask (ablation)AntiStyler · COCO, M-PGD patch (adversarial images)mAP@0.5: 35.3 -> 38.0Improved
VGG19 backbone instead of ResNet50 (ablation)AntiStyler · COCO, M-PGD patch (adversarial images)mAP@0.5: 32.4 -> 38.0Improved
VGG19 backbone instead of EfficientNetV2 (ablation)AntiStyler · COCO, Google patch (adversarial images)mAP@0.5: 24.2 -> 32.5Improved
apply AntiStyler against black-box adaptive patchAntiStyler · COCO adaptive attacksmAP@0.5: 23.4 -> 30.5Improved
apply AntiStyler against white-box adaptive patchAntiStyler · COCO adaptive attacksmAP@0.5: 18.7 -> 23.9Improved
AntiStyler vs PAD on printable patch P2AntiStyler · INRIA, natural patch P2mAP@0.5: 74.3 -> 74.4No clear effect
AntiStyler vs KDAT on DETR DPatchAntiStyler · COCO DPatch, DETRmAP@0.5: 45.5 -> 44.4Hurt

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