AI Paper Atlas

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

Merry Go Round: Rotate a Frame and Fool a DNN

Daksh Thapar, Aditya Nigam, Chetan Arora

CVPR 2022 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 1 citations (OpenAlex)

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
replace ME-Sampler with the proposed mixed intensity-and-rotation attackI3D · Kinetics-400 untargetedANQ: 2,717 -> 1,257Improved
replace ME-Sampler with the proposed mixed intensity-and-rotation attackRolling-Unrolling LSTM · Epic-Kitchens untargetedANQ: 7,326 -> 3,564Improved
replace V-Bad with the proposed mixed intensity-and-rotation attackEgoGaitNet · IITMD-FPR untargetedANQ: 5,480 -> 3,487Improved
replace ME-Sampler with the proposed mixed intensity-and-rotation attackI3D · Kinetics-400 targetedANQ: 11,120 -> 6,234Improved
replace ME-Sampler with the proposed mixed intensity-and-rotation attackRolling-Unrolling LSTM · Epic-Kitchens targetedANQ: 22,541 -> 15,283Improved
replace ME-Sampler with the proposed mixed intensity-and-rotation attackEgoGaitNet · IITMD-FPR targetedANQ: 18,759 -> 9,910Improved
use camera rotation only instead of the learned mixed perturbation (ablation)I3D attack · Kinetics-400SR%: 99.33 -> 38.19Hurt
use camera rotation only instead of the learned mixed perturbation (ablation)Rolling-Unrolling LSTM attack · Epic-KitchensSR%: 100.00 -> 62.81Hurt
use camera rotation only instead of the learned mixed perturbation (ablation)EgoGaitNet attack · IITMD-FPRSR%: 96.33 -> 58.42Hurt
use intensity-based perturbation only instead of the learned mixture (ablation)I3D attack · Kinetics-400ANQ: 1,257 -> 3,569Hurt
use intensity-based perturbation only instead of the learned mixture (ablation)Rolling-Unrolling LSTM attack · Epic-KitchensANQ: 3,564 -> 8,238Hurt
use intensity-based perturbation only instead of the learned mixture (ablation)EgoGaitNet attack · IITMD-FPRANQ: 3,487 -> 6,356Hurt

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