AI Paper Atlas

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

Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization

Xiang Fang, Wanlong Fang, Changshuo Wang

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 1 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 text attack (ablation)MMAS · DALLE-3, LLaVAOverall semantic similarity: 0.693 -> 0.872Improved
add image attack (ablation)MMAS · DALLE-3, LLaVAOverall semantic similarity: 0.681 -> 0.872Improved
add joint optimization of image and text perturbations (ablation)MMAS · DALLE-3, LLaVAOverall semantic similarity: 0.793 -> 0.872Improved
add texture constraint and cross-modal optimization over TC-UAPTC-UAP · MS-COCO, LLaVAOverall semantic similarity: 0.803 -> 0.883Improved
use MMAS instead of TA-UAPTA-UAP · MS-COCO, BLIP-2Overall semantic similarity: 0.799 -> 0.849Improved
raise texture scaling factor from 1 to 4 (ablation)MMAS · DALLE-3, LLaVA-1.5Overall semantic similarity: 0.823 -> 0.872Improved
raise texture scaling factor from 4 to 8 (ablation)MMAS · DALLE-3, LLaVA-1.5Overall semantic similarity: 0.872 -> 0.841Hurt
use MMAS instead of MF-AttackMF-Attack · ImageNet-1k VQAMean semantic similarity: 0.646 -> 0.839Improved
use MMAS instead of CroPACroPA · MS-COCO OpenFlamingoOverall ASR: 0.83 -> 0.89Improved
transfer MMAS adversarial examples instead of CroPA to GPT-4oCroPA · LLaVA to GPT-4oASR: 0.011 -> 0.379Improved
use MMAS instead of CroPA for generation costCroPA · LLaVA-1.5GPU time: 17 min -> 6 minImproved
change target text among six alternatives (ablation)MMAS · MS-COCO, FlamingoOverall semantic similarity: 0.868 to 0.895No clear effect

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