QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to provide incorrect answers. However, it is common for a single image to be associated with multiple questions, and LVLMs may still answer other questions correctly even for an adversarial image attacked by a specific question. To address this, we introduce the query-agnostic visual attack (QAVA), which aims to create robust adversarial examples that generate incorrect responses to unspecified and unknown questions. Compared to traditional adversarial attacks focused on specific images and questions, QAVA significantly enhances the effectiveness and efficiency of attacks on images when the question is unknown, achieving performance comparable to attacks on known target questions. Our research broadens the scope of visual adversarial attacks on LVLMs in practical settings, uncovering previously overlooked vulnerabilities, particularly in the context of visual adversarial threats. The code is available at https://github.com/btzyd/qava.
Code (1)
Tasks
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)Similar Papers 제목 키워드 기반
Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models
Despite significant improvements in natural language understanding models with the advent of models like BERT and XLNet, these neural-network based classifiers are vulnerable to blackbox adversarial attacks, where the at…
Adversarial AttackNatural Language UnderstandingQuISE: Defense against Typographic Attacks on VLMs via Query-Irrelevant Semantic Editing
Typographic attacks pose a critical threat to vision-language models (VLMs) by injecting misleading text into images and causing models to rely on adversarial textual cues rather than visual evidence. Existing defenses o…
Physical Prompt Injection Attacks on Large Vision-Language Models
Large Vision-Language Models (LVLMs) are increasingly deployed in real-world intelligent systems for perception and reasoning in open physical environments. While LVLMs are known to be vulnerable to prompt injection atta…
Visual Question AnsweringZero-Query Transfer Attacks on Context-Aware Object Detectors
Adversarial attacks perturb images such that a deep neural network produces incorrect classification results. A promising approach to defend against adversarial attacks on natural multi-object scenes is to impose a conte…
Adversarial AttackObjectJailbreak Vision Language Models via Bi-Modal Adversarial Prompt
In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks predominantly focus on the visual modality…
Language ModellingLarge Language ModelRed Teaming