AI Paper Atlas

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

Watch out! Motion is Blurring the Vision of Your Deep Neural Networks

Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jian Wang, Bing Yu, Wei Feng, Yang Liu

NeurIPS 2020 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 55 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
Use saliency-regularized motion blur with adaptively tuned object and background translations instead of pixel-wise independent kernels (ablation)ABBA · NeurIPS'17 adversarial competition dataset, Inc-v3success rate: 89.2 -> 65.6Hurt
Add adaptive joint object/background translations rather than using shared image-wide kernels and translations (ablation)ABBA · NeurIPS'17 adversarial competition dataset, Inc-v3success rate: 62.4 -> 65.6Improved
Restrict motion blur to the salient object (ablation)ABBA · NeurIPS'17 adversarial competition dataset, Inc-v3success rate: 65.6 -> 21.0Hurt
Restrict motion blur to the background (ablation)ABBA · NeurIPS'17 adversarial competition dataset, Inc-v3success rate: 65.6 -> 30.9Hurt
Increase the valid kernel size and maximum translation (ablation)ABBA · NeurIPS'17 adversarial competition datasetsuccess rateImproved
Set the object motion direction near 45° (ablation)ABBA · NeurIPS'17 adversarial competition datasetsuccess rateImproved
Use average kernels and shared object/background translation for physical camera motion instead of learned kernels and separate translations (ablation)ABBA_physical · AirSim cars, Inc-v3success rate: 97.6 -> 85.3Hurt
Use physical camera motion instead of the digitally generated adversarial blur (ablation)ABBA · AirSim cars, Inc-v4 transfersuccess rate: 87.8 -> 9.7Hurt
Use ABBA rather than TIDIMInc-v3-generated attacks · NeurIPS'17 adversarial competition dataset, Inc-v3 ens3success rate: 46.9 vs 46.6No clear effect
Use ABBA rather than TIDIMInc-v3-generated attacks · NeurIPS'17 adversarial competition dataset, HGDsuccess rate: 38.3 vs 31.0Hurt

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