Logo image
Back
Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models
Conference proceeding

Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models

Hao Cheng, Erjia Xiao, Jiayan Yang, Jinhao Duan, Yichi Wang, Jiahang Cao, Qiang Zhang, Le Yang, Kaidi Xu, Jindong Gu, …
Proceedings of the 33rd ACM International Conference on Multimedia, pp 5010-5019
27 Oct 2025
DOI: https://doi.org/10.1145/3746027.3755715

Abstract

Computing methodologies -- Artificial intelligence -- Computer vision Computing methodologies -- Artificial intelligence -- Natural language processing Computing methodologies -- Machine learning Security and privacy -- Software and application security
Multimodal Large Language Models (MLLMs) demonstrate exceptional performance in cross-modality interaction, yet they also suffer adversarial vulnerabilities. In particular, the transferability of adversarial examples remains an ongoing challenge. In this paper, we specifically analyze the manifestation of adversarial transferability among MLLMs and identify the key factors that influence this characteristic. We discover that the transferability of MLLMs exists in cross-LLM scenarios with the same vision encoder and indicate two key Factors that may influence transferability. We provide two semantic-level data augmentation methods, Adding Image Patch (AIP) and Typography Augment Transferability Method (TATM), which boost the transferability of adversarial examples across MLLMs. To explore the potential impact in the real world, we utilize two tasks that can have both negative and positive societal impacts: 1. Harmful Content Insertion and 2. Information Protection.

Metrics

6 Record Views

Details

Logo image