AI Paper Atlas

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

PBCAT: Patch-Based Composite Adversarial Training against Physically Realizable Attacks on Object Detection

Xiao Li, Yiming Zhu, Yifan Huang, Wei Zhang, Yingzhe He, Jie Shi, Xiaolin Hu

ICCV 2025 · Adversarial robustness and security › Attacks on text and graphs · approach: Physical adversarial patches and camouflage · 4 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 global imperceptible noise to patch adversarial training (ablation)PBCAT · Inria AdvPatchAP50: 35.4 -> 72.8Improved
add global imperceptible noise to patch adversarial training (ablation)PBCAT · Synthetic AdvTextureAP50: 1.6 -> 24.9Improved
add gradient-guided patch partition and selection (ablation)PBCAT · Synthetic AdvTextureAP50: 24.9 -> 63.3Improved
select top-50% sub-patches by gradient instead of random (ablation)PBCAT · Synthetic AdvTextureAP50: 14.2 -> 63.3Improved
use 64 sub-patches instead of 16 (ablation)PBCAT · Synthetic AdvTextureAP50: 50.8 -> 60.2Improved
use 64 sub-patches instead of pixel-level partition (ablation)PBCAT · Synthetic AdvTextureAP50: 20.4 -> 60.2Improved
enlarge sampled patch scale factor from 2sqrt2/10 to 4sqrt2/10 (ablation)PBCAT · Inria AdvPatch (16 sub-patches)AP50: 78.3 -> 63.4Hurt
raise top-k ratio from 50% to 70% (ablation)PBCAT · Synthetic AdvTextureAP50: 60.2 -> 19.0Hurt
lower top-k ratio from 50% to 30% (ablation)PBCAT · Inria AdvPatchAP50: 77.6 -> 51.3Hurt
use PBCAT instead of l_inf-AT (AdvOD)PBCAT · Synthetic AdvTextureAP50: 30.5 -> 60.2Improved
use PBCAT instead of l_inf-AT (AdvOD) on FCOSPBCAT · Inria AdvPatch (FCOS)AP50: 29.9 -> 58.0Improved
use PBCAT instead of non-AT preprocessing defensesPBCAT · Inria AdvPatchAP50: 57.1 -> 77.6Improved

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