AI Paper Atlas

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

REAP: A Large-Scale Realistic Adversarial Patch Benchmark

Nabeel Hingun, Chawin Sitawarin, Jerry Li, David Wagner

ICCV 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Physical adversarial patches and camouflage · 31 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
render patches on real signs with geometric and lighting transforms instead of on a synthetic signpatch attack evaluation on Faster R-CNN (small patch) · REAP-SASR: 73.1 -> 39.2Hurt
render patches on real signs instead of synthetic signpatch attack evaluation on YOLOF (small patch) · REAP-SASR: 88.6 -> 38.9Hurt
adversarial training of detectorsFaster R-CNN, large patch · REAPFNR: 50.0 -> 13.9Improved
adversarial training of detectorsDINO, large patch · REAPFNR: 62.8 -> 3.6Improved
adversarial training of detectorsclean performance · REAPmAP (no patch): FRCNN 72.9 -> 73.3; YOLOF FNR 18.5 -> 21.0Mixed
remove the relighting transform when rendering patches (ablation)YOLOF and Faster R-CNN · REAPmAP: mAP decreases by 17 points for YOLOF and 15 for Faster R-CNNHurt
use full perspective transform instead of affine or translate-and-scale (ablation)patch rendering · Realism test (44 samples)RMSE: 1.72 -> 1.13Improved
use percentile relighting in RGB instead of HSV or LAB (ablation)patch rendering · Realism test (44 samples)RMSE: 0.227 -> 0.110 (HSV vs RGB)Improved
use percentile relighting instead of polynomial fitting in RGB (ablation)patch rendering · Realism test (44 samples)RMSE: 0.113 -> 0.110No clear effect
per-instance attack instead of per-class patch against adversarially trained models (ablation)Adv. Faster R-CNN · REAP-S small patchASR: 5.1 -> 16.0Improved
add color-jitter or uniform noise augmentation to attack EoT (ablation)patch attack · REAPFNR / mAP: FRCNN FNR 15.4 -> 16.1 (jitter 0.1)No clear effect
transfer attack from another model instead of white-box per-class (ablation)Adv. Faster R-CNN · REAP-S small patchASR: 5.1 -> 2.7 (from Synthetic)Hurt

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