AI Paper Atlas

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

Adversarial Sticker: A Stealthy Attack Method in the Physical World

Xingxing Wei, Ying Guo, Jie Yu

TPAMI 2022 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition · 156 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 adaptive adjustment strategy to DE (ablation)DE · LFW dodging, FaceNetfooling rate: 29.03% -> 41.96%Improved
add region-based offspring generation to DE (ablation)DE · LFW dodging, FaceNetfooling rate: 29.03% -> 54.81%Improved
combine adaptive adjustment and region-based generation (RHDE) (ablation)DE · LFW dodging, FaceNetfooling rate: 29.03% -> 76.26%Improved
combine both strategies (RHDE) (ablation)DE · LFW dodging, FaceNetqueries: 1107 -> 478Improved
combine both strategies (RHDE) (ablation)DE · LFW dodging, SphereFacefooling rate: 21.88% -> 64.08%Improved
combine both strategies (RHDE) (ablation)DE · LFW dodging, CosFacefooling rate: 31.83% -> 69.82%Improved
use RHDE instead of exhaustive searchRHDE · LFW dodging, FaceNetfooling rate: 79.52% -> 76.26%No clear effect
model 3D deformation when solving sticker parameters (ablation)adversarial sticker · physical frames, FaceNet subject Aattack success rate: 59.78% -> 98.46%Improved
model 3D deformation when solving sticker parameters (ablation)adversarial sticker · physical frames, SphereFace subject Battack success rate: 33.33% -> 83.45%Improved
adversarially train with same sticker (sticker 2)target FaceNet · LFW dodgingfooling rate: 76.26% -> 60.35%Hurt
adversarially train with a different sticker (sticker 1)target FaceNet · LFW dodgingfooling rate: 76.26% -> 74.18%No clear effect
use RHDE sticker instead of adv-hatours vs adv-hat · LFW black-box, FaceNetfooling rate: 28.85% -> 76.26%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