Transferable Adversarial Attacks on Black-Box Vision-Language Models
Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary black-box models in text-only and vision-only contexts, the extent and effectiveness of such vulnerabilities remain underexplored for VLLMs. We present a comprehensive analysis demonstrating that targeted adversarial examples are highly transferable to widely-used proprietary VLLMs such as GPT-4o, Claude, and Gemini. We show that attackers can craft perturbations to induce specific attacker-chosen interpretations of visual information, such as misinterpreting hazardous content as safe, overlooking sensitive or restricted material, or generating detailed incorrect responses aligned with the attacker's intent. Furthermore, we discover that universal perturbations -- modifications applicable to a wide set of images -- can consistently induce these misinterpretations across multiple proprietary VLLMs. Our experimental results on object recognition, visual question answering, and image captioning show that this vulnerability is common across current state-of-the-art models, and underscore an urgent need for robust mitigations to ensure the safe and secure deployment of VLLMs.
Code (0)
등록된 구현이 없습니다.
Tasks
Image CaptioningObject RecognitionQuestion AnsweringVisual Question AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
When Background Matters: Breaking Medical Vision Language Models by Transferable Attack
Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objec…
When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
Vision-Language-Action (VLA) models are vulnerable to adversarial attacks, yet universal and transferable attacks remain underexplored, as most existing patches overfit to a single model and fail in black-box settings. T…
Strong Black-box Adversarial Attacks on Unsupervised Machine Learning Models
Machine Learning (ML) and Deep Learning (DL) models have achieved state-of-the-art performance on multiple learning tasks, from vision to natural language modelling. With the growing adoption of ML and DL to many areas o…
Adversarial AttackBIG-bench Machine LearningClusteringLanguage ModellingA Theory of Transfer-Based Black-Box Attacks: Explanation and Implications
Transfer-based attacks are a practical method of black-box adversarial attacks, in which the attacker aims to craft adversarial examples from a source (surrogate) model that is transferable to the target model. A wide ra…
Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning
Transfer learning has become a common practice for training deep learning models with limited labeled data in a target domain. On the other hand, deep models are vulnerable to adversarial attacks. Though transfer learnin…
Transfer Learning