AI Paper Atlas

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

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness

Sunoh Kim, Daeho Um

CVPR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 0 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 affine transform to augmentations (ablation)MAC · ten fine-grained avgrobust accuracy: 6.0 -> 45.2Improved
add Gaussian blur to augmentations (ablation)MAC · ten fine-grained avgrobust accuracy: 42.3 -> 45.2Improved
add Gaussian noise to augmentations (ablation)MAC · ten fine-grained avgrobust accuracy: 44.7 -> 45.2Improved
add color jitter to augmentations (ablation)MAC · ten fine-grained avgrobust accuracy: 44.9 -> 45.2Improved
add Gaussian blur to augmentations (ablation)MAC · ten fine-grained avgclean accuracy: 58.8 -> 58.7No clear effect
use corruption degree instead of noise-driven deviation for weighting (ablation)MAC · ten fine-grained avgrobust accuracy: +37.7%Improved
use multiple views instead of single view (ablation)MAC · ten fine-grained avgrobust accuracy: nearly 5 percentage pointsImproved
add more than two views (ablation)MAC · ten fine-grained avgrobust accuracyNo clear effect
increase counterattack iterations beyond K=4 (ablation)MAC · ten fine-grained avgrobust accuracyNo clear effect
raise counterattack budget from 4 to 8 (ablation)MAC · ten fine-grained avg, ViT-B/32robust accuracy: 33.7 -> 45.2Improved
raise counterattack budget from 4 to 8 (ablation)TTC · ten fine-grained avg, ViT-B/32robust accuracy: 6.8 -> 3.9Hurt
scale backbone from ViT-B/32 to ViT-L/14MAC · fine-grained avgrobust accuracy: 45.2 -> 61.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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