paper-with-me

Papers

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack

2025-02-27 · Chenhe Gu, Jindong Gu, Andong Hua, Yao Qin

Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the transferability of these attacks across different models remains limited, especially under targeted attack setting. Existing methods primarily focus on vision-specific perturbations but struggle with the complex nature of vision-language modality alignment. In this work, we introduce the Dynamic Vision-Language Alignment (DynVLA) Attack, a novel approach that injects dynamic perturbations into the vision-language connector to enhance generalization across diverse vision-language alignment of different models. Our experimental results show that DynVLA significantly improves the transferability of adversarial examples across various MLLMs, including BLIP2, InstructBLIP, MiniGPT4, LLaVA, and closed-source models such as Gemini.

📄 PDF Abstract BibTeX arXiv:2502.19672

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

Typography Leads Semantic Diversifying: Amplifying Adversarial Transferability across Multimodal Large Language Models

2024-05-30 · Hao Cheng, Erjia Xiao, Jiayan Yang, Jiahang Cao 외

Recently, Multimodal Large Language Models (MLLMs) achieve remarkable performance in numerous zero-shot tasks due to their outstanding cross-modal interaction and comprehension abilities. However, MLLMs are found to stil…

Diversity

How Robust is Google's Bard to Adversarial Image Attacks?

2023-09-21 · Yinpeng Dong, Huanran Chen, Jiawei Chen, Zhengwei Fang 외

Multimodal Large Language Models (MLLMs) that integrate text and other modalities (especially vision) have achieved unprecedented performance in various multimodal tasks. However, due to the unsolved adversarial robustne…

Adversarial RobustnessChatbotFace Detection

Image-based Multimodal Models as Intruders: Transferable Multimodal Attacks on Video-based MLLMs

2025-01-02 · Linhao Huang, Xue Jiang, Zhiqiang Wang, Wentao Mo 외

Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial videos to unseen models--a common and pr…

Adversarial AttackAttribute

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

2025-05-27 · Xiaojun Jia, Sensen Gao, Simeng Qin, Tianyu Pang 외

Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples. While existing methods typically achieve targeted attacks by aligning global features-such as CLIP's [CLS] token-between ad…

Adversarial AttackClustering

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs

2026-05-20 · Leitao Yuan, Qinghua Mao, Daizong Liu, Kun Wang 외 arxiv

Multimodal large language models (MLLMs) remain vulnerable to transfer-based targeted attacks, where perturbations optimized on open-source surrogate encoders can generalize to closed-source MLLMs. A key challenge for im…