AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Robustness of SAM: Segment Anything Under Corruptions and Beyond

Yu Qiao, Choong Seon Hong, Taegoo Kang, Dong-Hun Kim, Chenshuang Zhang, Sung‐Ho Bae, Chaoning Zhang

TPAMI 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 42 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 corruption severity from level 1 to 5 (Gaussian noise)SAM ViT-H · Common corruption (everything mode)mIoU: 0.8871 -> 0.7311Hurt
zoom blur versus other corruptionsSAM ViT-H · Common corruption (everything mode, severity 5)mIoU: 0.3739 vs 0.8334 (fog)Hurt
use larger backbone ViT-H instead of ViT-BSAM · Common corruption (everything mode, severity 5)mIoU: 0.5590 -> 0.6789 (JPEG)Improved
increase occlusion ratio from 20% to 80%SAM ViT-H · Local occlusion (point prompt)mIoU: 0.9234 -> 0.2290Hurt
apply adversarial patch of size 0.005 (point prompt)SAM · Adversarial patch attack (point prompt)mIoU: 0.0535Hurt
increase patch size from 0.005 to 0.05 (point prompt)SAM · Adversarial patch attack (point prompt)mIoU: 0.0535 -> 0.0545No clear effect
increase patch size from 0.005 to 0.02 (box prompt)SAM · Adversarial patch attack (box prompt)mIoU: 0.2084 -> 0.0427Hurt
use PGD-20 instead of FGSM at 8/255 (point prompt)SAM ViT-H · Global adversarial attack (point prompt)mIoU: 0.4600 -> 0.0172Hurt
use PGD-20 instead of FGSM at 8/255 (box prompt)SAM ViT-H · Global adversarial attack (box prompt)mIoU: 0.2764 -> 0.0110Hurt
increase PGD-20 epsilon from 0.1/255 to 8/255 (point prompt)SAM ViT-H · Global adversarial attack (point prompt)mIoU: 0.8020 -> 0.0172Hurt
use box prompt instead of point prompt for patch attack at 0.005SAM · Adversarial patch attackmIoU: 0.0535 -> 0.2084Mixed
style transfer to naturalism vs suprematismSAM · Style transfer (AdaIN, point prompt)mIoU: 0.7468 -> 0.6121Hurt

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