AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Over-the-Air Adversarial Flickering Attacks Against Video Recognition Networks

Roi Pony, Itay Naeh, Shie Mannor

CVPR 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 43 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
Use an optimized universal flickering perturbation instead of random MinMax flickeringVideo action recognition models · Kinetics-400 evaluation, $\ell_{\infty}[%]=20$fooling ratio: 48.0$\pm$ 4.5% -> 93.0%Improved
Use an optimized universal flickering perturbation instead of random MinMax flickeringVideo action recognition models · Kinetics-400 evaluation, $\ell_{\infty}[%]=20$fooling ratio: 42.0$\pm$ 3.0% -> 79.0%Improved
Use an optimized universal flickering perturbation instead of random MinMax flickeringVideo action recognition models · Kinetics-400 evaluation, $\ell_{\infty}[%]=20$fooling ratio: 54.6$\pm$ 11.0% -> 90.3%Improved
Use an optimized universal flickering perturbation instead of random MinMax flickeringVideo action recognition models · Kinetics-400 evaluation, $\ell_{\infty}[%]=20$fooling ratio: 44.0$\pm$ 5.0% -> 77.1%Improved
Add a random temporal shift during training and evaluation (ablation)Universal flickering attack on I3D · Kinetics-400 testfooling ratio: 93.0 -> 83.1Hurt
Add roughness regularization rather than minimizing thickness alone (ablation)Single-video flickering attack on I3D · Kinetics-400 test, single video exampleroughness: 4.84\% -> 2.20\%Improved
Add roughness regularization rather than minimizing thickness alone (ablation)Single-video flickering attack on I3D · Kinetics-400 test, single video examplethickness: 2.97\% -> 7.45\%Hurt
Use one universal perturbation across videos instead of video-specific perturbationsFlickering attack on I3D · Kinetics-400fooling ratio: 100 -> 93.0Mixed
Use a class-specific generalized perturbation instead of a video-specific perturbationFlickering attack on I3D · Kinetics-400fooling ratio: 100 -> 90.2$\pm$ 11.72Mixed

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