AI Paper Atlas

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

Sparse Adversarial Perturbations for Videos

Xingxing Wei, Jun Zhu, Sha Yuan, Hang Su

AAAI 2019 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 151 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
Increase the proportion of clean frames to 97.5%, leaving one perturbed frame (ablation)Sparse adversarial perturbations · UCF101 testfooling rate: 100% -> 59.7%Hurt
Increase sparsity from 80% to 90% (ablation)Sparse adversarial perturbations · UCF101 testfooling rate: 100% -> 91.8%Hurt
Use l2,1 regularization instead of l2 regularization (ablation)Video perturbation optimization · UCF101temporal sparsityImproved
Use l2 regularization rather than l2,1 when perturbing selected frames for propagation to the rest (ablation)Shortened-video propagation attack · UCF101fooling rateImproved
Add a temporal mask to keep frames outside the selected top 8 clean (ablation)Sparse adversarial perturbations · UCF101 videosframe-level misclassificationImproved
Replace VanillaRNN with LSTM or GRU (ablation)CNN+RNN video attack · UCF101fooling rate: 84.1% -> 100% (LSTM); 81.8% -> 100% (GRU)Improved
Remove the RNN layer and use CNN + Average Pooling (ablation)CNN+RNN video attack · UCF101fooling rate: 100% -> 87.3%Hurt
Use perturbations trained on the training videos on unseen test videosUniversal perturbations · UCF101 testfooling rate: 100% (training set); 95.2% (testing set)Improved
Compute perturbations on fewer frames of a shortened video (ablation)Propagation-based attack · UCF101, one optimization iterationcomputation time: 2.853s -> 0.0947sImproved

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