Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation
Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting the unsafe responses, we observe that safety mechanisms of the pre-aligned LLMs in MLLMs can be easily bypassed with the introduction of image features. To construct robust MLLMs, we propose ECSO (Eyes Closed, Safety On), a novel training-free protecting approach that exploits the inherent safety awareness of MLLMs, and generates safer responses via adaptively transforming unsafe images into texts to activate the intrinsic safety mechanism of pre-aligned LLMs in MLLMs. Experiments on five state-of-the-art (SoTA) MLLMs demonstrate that ECSO enhances model safety significantly (e.g.,, 37.6% improvement on the MM-SafetyBench (SD+OCR) and 71.3% on VLSafe with LLaVA-1.5-7B), while consistently maintaining utility results on common MLLM benchmarks. Furthermore, we show that ECSO can be used as a data engine to generate supervised-finetuning (SFT) data for MLLM alignment without extra human intervention.
Code (0)
등록된 구현이 없습니다.
Tasks
Image to textOptical Character Recognition (OCR)Similar Papers 제목 키워드 기반
ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models
While multimodal large language models (MLLMs) extend model capabilities beyond text, they also make safety alignment increasingly challenging. Multimodal safety alignment methods must address cross-modal jailbreaks, saf…
Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration
Large Language Models (LLMs) have demonstrated remarkable capabilities in challenging, knowledge-intensive reasoning tasks. However, extending LLMs to perceive and reason over a new modality (e.g., vision), often require…
Multimodal ReasoningBy My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting
Large language models (LLMs) have demonstrated exceptional abilities across various domains. However, utilizing LLMs for ubiquitous sensing applications remains challenging as existing text-prompt methods show significan…
Visual PromptingJailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Multimodal Large Language Models (MLLMs) have achieved impressive performance and have been put into practical use in commercial applications, but they still have potential safety mechanism vulnerabilities. Jailbreak att…
Red TeamingWith Ears to See and Eyes to Hear: Sound Symbolism Experiments with Multimodal Large Language Models
Recently, Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated aptitude as potential substitutes for human participants in experiments testing psycholinguistic phenomena. However, an understud…