AI Paper Atlas

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

Bias-based Universal Adversarial Patch Attack for Automatic Check-out

Aishan Liu, Jiakai Wang, Xianglong Liu, Bowen Cao, Chongzhi Zhang, Hang Yu

ECCV 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition · 132 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
initialize patch with the fused textural prior instead of simple fusion of simple examples (ablation)Bias-based patch · RPC white-box (ResNet-152)top-1 accuracy after attack: 24.09 -> 5.42Improved
initialize patch with the fused textural prior instead of a white patch (ablation)Bias-based patch · RPC white-box (ResNet-152)top-1 accuracy after attack: 17.67 -> 5.42Improved
train with 1000 prototypes instead of 1000 item images (ablation)Bias-based patch · RPC (ResNet-152)top-1 accuracy after attack: 12.43 -> 6.51Improved
replace item images with prototypes in the training mix (750 : 250) (ablation)Bias-based patch · RPC (ResNet-152)top-1 accuracy after attack: 12.43 -> 7.81Improved
use 500 prototypes plus 500 item images instead of 1000 item images (ablation)Bias-based patch · RPC (ResNet-152)top-1 accuracy after attack: 12.43 -> 10.03Improved
use 250 prototypes plus 750 item images instead of 1000 item images (ablation)Bias-based patch · RPC (ResNet-152)top-1 accuracy after attack: 12.43 -> 11.55Improved
use 10000 item images instead of 1000 prototypes (ablation)Bias-based patch · RPC (ResNet-152)top-1 accuracy after attack: 6.51 -> 5.40Mixed
use 2000 item images instead of 1000 item images (ablation)Bias-based patch · RPC (ResNet-152)top-1 accuracy after attack: 12.43 -> 6.57Improved
add rotation transformation during training (ablation)Bias-based patch · RPC (ResNet-152)top-1 accuracy after attack: 13.01 -> 11.98Improved
add distortion transformation during training (ablation)Bias-based patch · RPC (ResNet-152)top-1 accuracy after attack: 30.70 -> 22.26Improved
add affine transformation during training (ablation)Bias-based patch · RPC (ResNet-152)top-1 accuracy after attack: 21.10 -> 16.38Improved
use proposed method vs best compared method on unseen classesBias-based patch · RPC unseen classestop-1 accuracy after attack: 31.62 -> 7.23Improved

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