AI Paper Atlas

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

Stereoscopic Universal Perturbations Across Different Architectures and Datasets

Zachary Berger, Parth Agrawal, Tian Yu Liu, Stefano Soatto, Alex Wong

CVPR 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Biologically inspired robust vision · 8 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
Add an image-agnostic SUP optimized for the attacked modelAANet, DeepPruner, and PSMNet · KITTI 2015D1-error: 1.47% -> 48.43%; 1.28% -> 52.74%; 4.25% -> 87.72%Hurt
Transfer AANet-optimized SUPs across architecturesDeepPruner and PSMNet · KITTI 2015D1-error: 1.28% to 52.66%; 4.25% to 61.66%Hurt
Apply KITTI-optimized SUPs to models trained on Scene FlowAANet, DeepPruner, and PSMNet · FlyingThings3DEPE: 1.30px to 9.47px; 1.25px to 14.77px; 1.27px to 18.88pxHurt
Use a 64 x 64 tiled SUP instead of a full-image SUP (ablation)AANet, DeepPruner, and PSMNet · FlyingThings3Dreported error: 36.09% -> 46.14%; 23.28% -> 34.87%; 25.35% -> 31.93%Hurt
Use a 64 x 64 tile instead of a 128 x 128 tile (ablation)AANet, DeepPruner, and PSMNet · FlyingThings3Dreported error: 40.84% -> 46.14%; 27.89% -> 34.87%; 29.33% -> 31.93%Hurt
Increase the tile size from 64 x 64 to 128 x 128 (ablation)AANet · KITTI 2015D1-errorImproved
Add deformable convolutions (ablation)DeepPruner and PSMNet · KITTI 2015D1-error: 52.74% -> 39.47%; 87.72% -> 52.10%Improved
Replace deformable convolutions with regular convolutions (ablation)AANet · KITTI 2015D1-error: 48.43% -> 54.32%Hurt
Increase deformable convolutions from 6 to 25, then add explicit matching (ablation)PSMNet · KITTI 2015D1-error: 87.72% to 66.10%, 52.10%, and finally to 39.47%Improved
Fine-tune with adversarial data augmentation (ablation)AANet, DeepPruner, and PSMNet · KITTI 2015D1-error: 48.43% to 3.62%; 52.74% to 2.83%; 87.72% to 2.96%Improved
Fine-tune with adversarial data augmentation against a newly optimized adversary (ablation)AANet, DeepPruner, and PSMNet · KITTI 2015D1-error: 25.54%; 31.54%; 35.75%Mixed
Combine 25 deformable convolutions and explicit matching (ablation)PSMNet · KITTI 2015D1-error: 87.72% -> 39.47%Improved

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