AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Adversarial Bone Length Attack on Action Recognition

Nariki Tanaka, Hiroshi Kera, Kazuhiko Kawamoto

AAAI 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 15 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
Train with data augmentation (ablation)ST-GCN on HDM05 · HDM05clean accuracy: 86.1% -> 89.8%Improved
Train with data augmentation (ablation)SGN on HDM05 · HDM05clean accuracy: 95.3% -> 96.1%Improved
Train with data augmentation (ablation)ST-GCN on HDM05 · HDM05 bone-length attackattack success rateHurt
Train with data augmentation (ablation)SGN on HDM05 · HDM05 bone-length attackattack success rateHurt
Adversarially train with bone-length attacks at ε=0.1 (ablation)ST-GCN on HDM05 · HDM05clean accuracy: 86.1% -> 89.8%Improved
Adversarially train with bone-length attacks at ε=0.1 (ablation)SGN on HDM05 · HDM05clean accuracy: 96.1% -> 95.5%Hurt
Adversarially train with bone-length attacks at ε=0.1 (ablation)ST-GCN on HDM05 · HDM05 bone-length attackattack success rateHurt
Adversarially train with bone-length attacks at ε=0.1 (ablation)SGN on HDM05 · HDM05 bone-length attackattack success rateHurt
Restrict perturbations to Part 6 (legs) rather than other individual parts (ablation)Bone length attack on ST-GCN · HDM05attack success rate: 34.1% vs 0.00% to 12.6% at ε=0.1Improved
Perturb Parts 3, 4, and 5 together instead of Part 6 (ablation)Bone length attack on ST-GCN · HDM05, ε=0.3attack success rate: 75.8% -> 59.6%Hurt
Continue the attack for the full run rather than stop at first success (ablation)Bone length attack on ST-GCN · HDM05 adversarial examplesaverage confidence: 51.3% -> 50.4%No clear effect
Perturb bones that are longer and closer to the root jointBone length attack · HDM05attack success rateImproved

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