Adversarial Confusion Attack: Disrupting Multimodal Large Language Models
We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model generate incoherent or confidently incorrect outputs. Practical applications include embedding such adversarial images into websites to prevent MLLM-powered AI Agents from operating reliably. The proposed attack maximizes next-token entropy using a small ensemble of open-source MLLMs. In the white-box setting, we show that a single adversarial image can disrupt all models in the ensemble, both in the full-image and Adversarial CAPTCHA settings. Despite relying on a basic adversarial technique (PGD), the attack generates perturbations that transfer to both unseen open-source (e.g., Qwen3-VL) and proprietary (e.g., GPT-5.1) models.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring…
Adversarial RobustnessLocalize and Neutralize: Gradient-guided Token Suppression against Visual Prompt Injection Attack
Adversarial images pose a severe security threat to multimodal large language models through prompt injection. Existing defenses largely lack a principled understanding of the underlying mechanisms and struggle to balanc…
Adversarial AttackMisaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
Multimodal Language Models (MMLMs) typically undergo post-training alignment to prevent harmful content generation. However, these alignment stages focus primarily on the assistant role, leaving the user role unaligned, …
Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems
Face modification systems using deep learning have become increasingly powerful and accessible. Given images of a person's face, such systems can generate new images of that same person under different expressions and po…
Adversarial AttackAttributeTranslationBreak the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities. However, the visual modules introduces new challenges in terms …