AI Paper Atlas

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

BASAR:Black-Box Attack on Skeletal Action Recognition

Yunfeng Diao, Tianjia Shao, Yong-Liang Yang, Kun Zhou, He Wang

CVPR 2021 · Adversarial robustness and security › Black-box and transfer attacks · approach: Decision-based boundary attacks

Check 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 BASAR instead of the strongest reported baselineskeletal action recognizers · HDM05 and NTU targeted attacksuccess rate: 30.31% -> 100.00%Improved
use BASAR instead of SMART (HRNN)skeletal action recognizers · HDM05 untargeted attacksuccess rate: 89.25% -> 100.00%Improved
use BASAR instead of SMART (HRNN)skeletal action recognizers · NTU untargeted attacksuccess rate: 99.33% -> 100.00%Improved
add manifold projection (ablation)BASAR, HDM05 untargeted on STGCN · HDM05on-manifold sample percentage: 0.00% -> 99.55%Improved
add manifold projection (ablation)BASAR, HDM05 untargeted on STGCN · HDM05joint angular acceleration deviation: 0.34 -> 0.11Improved
add manifold projection (ablation)BASAR, HDM05 untargeted on STGCN · HDM05bone-length deviation: 0.66% -> 0.00%Improved
add manifold projection (ablation)BASAR, HDM05 untargeted on STGCN · HDM05joint position deviation: 0.10 -> 0.13Hurt
add manifold projection (ablation)BASAR, HDM05 targeted on STGCN · HDM05on-manifold sample percentage: 0.00% -> 56.98%Improved
add manifold projection (ablation)BASAR · HDM05 perceptual naturalnessnaturalness preferenceImproved
use semantic joint featuresSGN compared with STGCN and MSG3D · HDM05, NTU, and Kinetics attacksperturbation required to fool the classifierImproved
use explicit bone informationMSG3D compared with STGCN · skeletal action recognition attacksrobustness to attackImproved
apply BASAR rather than the white-box attack in the cited workHDM05 perceptual indistinguishability study · HDM05indistinguishability: 80.83% -> 89.90%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