Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time
Recently, Multimodal Large Language Models (MLLMs) have gained significant attention across various domains. However, their widespread adoption has also raised serious safety concerns. In this paper, we uncover a new safety risk of MLLMs: the output preference of MLLMs can be arbitrarily manipulated by carefully optimized images. Such attacks often generate contextually relevant yet biased responses that are neither overtly harmful nor unethical, making them difficult to detect. Specifically, we introduce a novel method, Preference Hijacking (Phi), for manipulating the MLLM response preferences using a preference hijacked image. Our method works at inference time and requires no model modifications. Additionally, we introduce a universal hijacking perturbation -- a transferable component that can be embedded into different images to hijack MLLM responses toward any attacker-specified preferences. Experimental results across various tasks demonstrate the effectiveness of our approach. The code for Phi is accessible at https://github.com/Yifan-Lan/Phi.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Vera Verto: Multimodal Hijacking Attack
The increasing cost of training machine learning (ML) models has led to the inclusion of new parties to the training pipeline, such as users who contribute training data and companies that provide computing resources. Th…
Decoderimage-classificationImage ClassificationSemantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation
Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-Aware Hijacking. We explore the feasibili…
Autonomous DrivingVocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet their reliability is persistently undermined by hallucinations-generating text that contradicts visual input. Recent studies…
BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF
Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning text-to-image (T2I) models with human preferences. However, RLHF's feedback mechanism also opens new pathways for adversaries. This paper demonstr…
From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG
Multimodal RAG systems increasingly rely on vision-language retrievers to ground visual queries in external textual evidence. Existing adversarial studies on RAG mainly manipulate the retrieval corpus or memory, while at…