AI Paper Atlas

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

Patch-wise Attack for Fooling Deep Neural Network

Lianli Gao, Qilong Zhang, Jingkuan Song, Xianglong Liu, Heng Tao Shen

ECCV 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition · 168 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 patch-wise project kernel on top of MI-FGSM-style baseline (PI-FGSM vs MI-FGSM)MI-FGSM, source Inc-v3 · NT target Dense-161success rate (%): 45.8 -> 61.7Improved
add PI to DMI-FGSM (DMPI-FGSM)DMI-FGSM, source Inc-v3 · NT target Inc-v4success rate (%): 78.9 -> 81.8Improved
add PI to DMI-FGSM (DMPI-FGSM)DMI-FGSM, source IncRes-v2 · NT target Inc-v3success rate (%): 86.8 -> 92.2Improved
add PI to DTMI-FGSM (DTPI-FGSM)DTMI-FGSM, ensemble source · EAT target Inc-v3_ens3success rate (%): 81.2 -> 89.3Improved
add PI to DTMI-FGSM (DTPI-FGSM)DTMI-FGSM, ensemble source · FD target ResNeXt_DAsuccess rate (%): 6.1 -> 11.7Improved
add PI to DTMI-FGSM when single source IncRes-v2DTMI-FGSM · EAT target IncRes-v2_enssuccess rate (%): 62.9 -> 62.3No clear effect
add PI to MI-FGSM with source IncRes-v2 (PI-FGSM vs MI-FGSM)MI-FGSM · NT target Inc-v3success rate (%): 77.6 -> 76.1Hurt
increase project factor gamma from 1.0 to 16.0 (ablation)PI-FGSM, source Inc-v3 · avg of 8 black-box modelsaverage success rate (%): 24.5 -> 46.2Improved
increase project factor gamma from 3.0 to 16.0 (ablation)DMPI-FGSM, source Inc-v3 · NT averageaverage success rate (%): 72.6 -> 57.4Hurt
increase project factor gamma from 1.0 to 16.0 (ablation)PI-FGSM, source Res152_B · FD averageaverage success rate (%): 70.7 -> 58.5Hurt
increase iterations T from 5 to 30 (ablation)PI-FGSM, source Inc-v3 · NT averageaverage success rate (%): 55.2 -> 53.8No clear effect
increase iterations T from 5 to 30 (ablation)PI-FGSM, source Inc-v3 · EAT averageaverage success rate (%): 23.0 -> 28.3Improved

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