AI Paper Atlas

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

GLEAM: Enhanced Transferable Adversarial Attacks for Vision-Language Pre-training Models via Global-Local Transformations

Yunqi Liu, Xue Ouyang, Xiaohui Cui

ICCV 2025 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 4 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 NURBS local deformation and global distribution expansion to the attack (ablation)GLEAM · ALBEF -> CLIP-CNN, Flickr30K TRattack success rate (%): to 80.7 (TR) and 81.3 (IR) with LFE+GDEImproved
add cross-modal feature alignment using intermediate adversarial images (ablation)GLEAM (LFE+GDE) · ALBEF -> CLIP-CNN, Flickr30Kattack success rate (%): +6.0 TR, +5.3 IR points (80.7 -> 86.7 TR)Improved
use LFE alone instead of SGA/SA-AET augmentation (ablation)GLEAM · ALBEF -> CLIP-CNNattack success rate (%)Improved
replace SA-AET with GLEAM for black-box transfer to MLLMsGPT-4o · MLLM attack success rateattack success rate (%): 6% -> 39%Improved
replace SA-AET with GLEAM for cross-model transferALBEF source, CLIP-ViT target · Flickr30K TRattack success rate (%): 55.58 -> 86.66Improved
replace SA-AET with GLEAM in white-box settingALBEF/TCL source and target · Flickr30K/MSCOCOattack success rate (%)No clear effect
increase image perturbation budget epsilon_v (ablation)GLEAM · TR attack successattack success rateImproved
apply defenses (NRP, JPEG, DiffPure, etc.) against GLEAMGLEAM · ITR with defensesTR R@1: ALBEF TR 73.04 under NRP+LTMixed
replace SA-AET with GLEAM for cross-task transfer to captioningITR adversarial examples · MSCOCO captioningCIDEr: 64.0 -> 56.2Improved

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