Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
In this paper, we study the harmlessness alignment problem of multimodal large language models (MLLMs). We conduct a systematic empirical analysis of the harmlessness performance of representative MLLMs and reveal that the image input poses the alignment vulnerability of MLLMs. Inspired by this, we propose a novel jailbreak method named HADES, which hides and amplifies the harmfulness of the malicious intent within the text input, using meticulously crafted images. Experimental results show that HADES can effectively jailbreak existing MLLMs, which achieves an average Attack Success Rate (ASR) of 90.26% for LLaVA-1.5 and 71.60% for Gemini Pro Vision. Our code and data are available at https://github.com/RUCAIBox/HADES.
Code (2)
Similar Papers 제목 키워드 기반
Achilles Heels for AGI/ASI via Decision Theoretic Adversaries
As progress in AI continues to advance, it is important to know how advanced systems will make choices and in what ways they may fail. Machines can already outsmart humans in some domains, and understanding how to safely…
Tackling Sparsity, the Achilles Heel of Social Networks: Language Model Smoothing via Social Regularization
Linear Phase Retrieval for Near-Field Measurements with Locally Known Phase Relations
A linear and thus convex phase retrieval algorithm for the application in phaseless near-field far-field transformations is presented. The formulation exploits locally known phase relations among sets of measurement samp…
RetrievalBoosting the Robustness Verification of DNN by Identifying the Achilles's Heel
Deep Neural Network (DNN) is a widely used deep learning technique. How to ensure the safety of DNN-based system is a critical problem for the research and application of DNN. Robustness is an important safety property o…
Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models
Large Multimodal Models (LMMs) have demonstrated the ability to interact with humans under real-world conditions by combining Large Language Models (LLMs) and modality encoders to align multimodal information (visual and…
Red TeamingSafety Alignment