AI Paper Atlas

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

Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches

Zhiyuan Cheng, James Liang, Hongjun Choi, Guanhong Tao, Zhiwen Cao, Dongfang Liu, Xiangyu Zhang

ECCV 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Latency and driving-perception attacks · 110 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
add object-oriented adversarial loss (no regional optimization) (ablation)patch attack on Monodepth2 · vehicle, KITTImean depth estimation error Ed: 8.47 -> 14.95Improved
add regional optimization without object-oriented loss (ablation)patch attack on Monodepth2 · vehicle, KITTImean depth estimation error Ed: 8.47 -> 6.38Hurt
add regional optimization on top of object-oriented loss (ablation)patch attack on Monodepth2 · vehicle, KITTImean depth estimation error Ed: 14.95 -> 16.84Improved
add regional optimization on top of object-oriented loss (ablation)patch attack on Monodepth2 · vehicle, KITTIratio of affected region Ra: 0.52 -> 0.65Improved
replace location-optimized patch with sensitive region localizationpatch attack on Monodepth2 · vehicle, KITTImean depth estimation error Ed: 13.90 -> 16.84Improved
replace location-optimized patch with sensitive region localizationpatch attack on DepthHints · vehicle, KITTImean depth estimation error Ed: 2.51 -> 15.23Improved
replace location-optimized patch with sensitive region localizationpatch attack on Manydepth · vehicle, KITTImean depth estimation error Ed: 3.03 -> 6.31Improved
raise style transfer weight from 1 to 10 (ablation)patch attack on Monodepth2 · vehicle, KITTImean depth estimation error Ed: 7.69 -> 1.44Hurt
lower style transfer weight from 1 to 0.1 (ablation)patch attack on Monodepth2 · vehicle, KITTImean depth estimation error Ed: 7.69 -> 11.09Improved
raise style transfer weight from 1 to 100 (ablation)patch attack on Monodepth2 · vehicle, KITTISSIM to style image: 0.575 -> 0.993Improved
enlarge patch from 1/9 to 1/3 of rear area (ablation)patch attack on Monodepth2 · PointPillars 3D detectionattack success rate: 95% -> 100%Improved
enlarge patch from 1/9 to 2/9 of rear area (ablation)patch attack on DepthHints · PointPillars 3D detectionattack success rate: 93% -> 97%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