Universal Adversarial Attack on Aligned Multimodal LLMs
We propose a universal adversarial attack on multimodal Large Language Models (LLMs) that leverages a single optimized image to override alignment safeguards across diverse queries and even multiple models. By backpropagating through the vision encoder and language head, we craft a synthetic image that forces the model to respond with a targeted phrase (e.g., ''Sure, here it is'') or otherwise unsafe content-even for harmful prompts. In experiments on the SafeBench benchmark, our method achieves significantly higher attack success rates than existing baselines, including text-only universal prompts (e.g., up to 93% on certain models). We further demonstrate cross-model transferability by training on several multimodal LLMs simultaneously and testing on unseen architectures. Additionally, a multi-answer variant of our approach produces more natural-sounding (yet still malicious) responses. These findings underscore critical vulnerabilities in current multimodal alignment and call for more robust adversarial defenses. We will release code and datasets under the Apache-2.0 license. Warning: some content generated by Multimodal LLMs in this paper may be offensive to some readers.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackSimilar Papers 제목 키워드 기반
Visual Adversarial Examples Jailbreak Aligned Large Language Models
Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and sa…
AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs
As large language models (LLMs) become increasingly prevalent and integrated into autonomous systems, ensuring their safety is imperative. Despite significant strides toward safety alignment, recent work GCG~\citep{zou20…
Safety AlignmentAlign is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the n…
Safety AlignmentEnhancing Adversarial Attacks through Chain of Thought
Large language models (LLMs) have demonstrated impressive performance across various domains but remain susceptible to safety concerns. Prior research indicates that gradient-based adversarial attacks are particularly ef…
Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization
Targeted adversarial attacks on closed-source multimodal large language models (MLLMs) have been increasingly explored under black-box transfer, yet prior methods are predominantly sample-specific and offer limited reusa…