AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Distributionally Location-Aware Transferable Adversarial Patches for Facial Images

Xingxing Wei, Shouwei Ruan, Yinpeng Dong, Hang Su, Xiaochun Cao

TPAMI 2025 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition · 11 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 DOP-DTA distribution transfer attack instead of DOP-Rd random sampling (ablation)DOPatch · LFW face classification SphereFaceattack success rate: 36.6% -> 61.9%Improved
use DOP-LOA location optimization instead of random sampling (ablation)DOPatch · LFW face classification FaceNetnumber of queries: 219 -> 110Improved
use distribution prior (DOP-DTA) instead of RHDERHDE · LFW face classification SphereFaceattack success rate: 31.3% -> 61.9%Improved
use distribution prior (DOP-DTA) instead of RHDERHDE · LFW face identification ArcFacenumber of queries: 2695 -> 492Improved
use mean location of distribution (DOP) instead of GDPA white-box locationGDPA · LFW face classification FaceNetattack success rate: 53.0% -> 72.6%Improved
increase Gaussian components K from 1 to 5 (ablation)DOPatch query attacks · LFW face classificationattack success rateImproved
increase Gaussian components K beyond 5 (ablation)DOPatch query attacks · LFW face classificationattack success rateNo clear effect
use K=5 components in DOP-DMAT instead of K=1 (ablation)DOP-DMAT · FaceNet RHDE attackattack success rate: 12.9% -> 4.5%Improved
use FaceNet as surrogate instead of SphereFace or MobileFaceNet (ablation)DOPatch · face classificationattack success rateImproved
set entropy regularization lambda to 0.1 (ablation)DOPatch · FaceNet surrogateadversarial loss convergenceImproved
use meaningful cartoon sticker patterns instead of LaVAN or Gaussian noise (ablation)DOPatch · face classificationattack success rateImproved
use DOP-DMAT adversarial training instead of standard trainingFaceNet · LFW face classification, RHDE attackattack success rate: 42.2% -> 4.5%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