AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Transform to Transfer: Boosting Adversarial Attack Transferability on Vision-Language Pre-training Models

Yang Li, Jia-Li Yin, Luojun Lin, Wei Lin

CVPR 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples

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 learnable block-level transformation and boosted integrated gradients to SGA-style attack (ablation)TTA · Flickr30K, ALBEF to CLIP-ViT/CLIP-CNN/TCLattack success rateImproved
add standard integrated gradients (20 points) in place of standard gradients (ablation)SGA-style attack · Flickr30K, ALBEF sourceattack success rateImproved
add learnable transformation (without boosted IG) (ablation)TTA · Flickr30K, ALBEF sourceattack success rateImproved
increase number of auxiliary transformed images Q_O beyond 30 (ablation)TTA · Flickr30K, ALBEF sourceattack success rateNo clear effect
increase block-level transformations L from 1 to 2 (ablation)TTA · Flickr30K, ALBEF sourceattack success rateImproved
increase block-level transformations L beyond 2 (ablation)TTA · Flickr30K, ALBEF sourceTR/IR R@1 and R@5Hurt
use image-text-image (i-t-i) attack process instead of shorter or longer cycles (ablation)TTA · Flickr30K, ALBEF source, avg of TCL/CLIP-ViT/CLIP-CNNattack success rateImproved
replace LSSA with TTA at 20 augmented imagesALBEF source attack · Flickr30K, target CLIP-ViTTR R@1 attack success rate (%): 53.25 -> 89.08Improved
add learnable transformations compared with LSSATTA · Flickr30K, ALBEF source, 20 augmented imagesrunning time (s): 27.33 -> 28.44Hurt

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