AI Paper Atlas

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

Targeted Adversarial Perturbations for Monocular Depth Prediction

Alex Wong, Safa Cicek, Stefano Soatto

NeurIPS 2020 · Adversarial robustness and security › Attacks on text and graphs · approach: Biologically inspired robust vision · 1 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 proposed loss instead of DAG for scene scalingtargeted perturbation · KITTI scaling +-5%/+-10%absolute relative errorImproved
increase perturbation norm xi from 2e-3 to 2e-2 (ablation)targeted perturbation · KITTI scaling +-10%absolute relative error: 3% -> 0.5%Improved
horizontally flip instead of scaling by +10%targeted perturbation · KITTI, xi=2e-2L1 norm of perturbation: 0.0161 -> 0.0326Hurt
vertical flip instead of horizontal fliptargeted perturbation · KITTIattack successHurt
apply Gaussian blur defense at xi=2e-2 (ablation)Monodepth2 · KITTI scaling +-10%absolute relative error: 3%Mixed
adversarially train Monodepth2 (ablation)Monodepth2 · KITTI scaling +-10%, xi=2e-3absolute relative error: 7%Mixed
adversarial training versus Gaussian blur at large xi (ablation)defense · KITTI scalingabsolute relative errorImproved
adversarial training versus Gaussian blur at small xi (ablation)defense · KITTI scalingabsolute relative errorNo clear effect
constrain perturbation within instance mask (ablation)targeted perturbation · Instance removalremoval successHurt
constrain perturbation outside instance mask (ablation)targeted perturbation · Instance removalremoval successMixed
target traffic sign and human instead of vehicle and naturecategory scaling · alpha=+-10%absolute relative error: 1% -> 6%Hurt
increase scale beyond 15% with xi=2e-3 (ablation)targeted perturbation · larger scalingabsolute relative error: approximately 4% for every 5% increaseHurt

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