Safety Alignment for Vision Language Models
Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs is vulnerable, with attackers easily bypassing LLMs' safety alignment through visual modality features to launch attacks. To address this issue, we enhance the existing VLMs' visual modality safety alignment by adding safety modules, including a safety projector, safety tokens, and a safety head, through a two-stage training process, effectively improving the model's defense against risky images. For example, building upon the LLaVA-v1.5 model, we achieve a safety score of 8.26, surpassing the GPT-4V on the Red Teaming Visual Language Models (RTVLM) benchmark. Our method boasts ease of use, high flexibility, and strong controllability, and it enhances safety while having minimal impact on the model's general performance. Moreover, our alignment strategy also uncovers some possible risky content within commonly used open-source multimodal datasets. Our code will be open sourced after the anonymous review.
Code (0)
등록된 구현이 없습니다.
Tasks
Red TeamingSafety AlignmentSimilar Papers 제목 키워드 기반
Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
Vision-language alignment in Large Vision-Language Models (LVLMs) successfully enables LLMs to understand visual input. However, we find that existing vision-language alignment methods fail to transfer the existing safet…
Visual Question AnsweringVLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap
The emergence of vision language models (VLMs) comes with increased safety concerns, as the incorporation of multiple modalities heightens vulnerability to attacks. Although VLMs can be built upon LLMs that have textual …
AttributeSafety AlignmentUnfair Alignment: Examining Safety Alignment Across Vision Encoder Layers in Vision-Language Models
Vision-language models (VLMs) have improved significantly in multi-modal tasks, but their more complex architecture makes their safety alignment more challenging than the alignment of large language models (LLMs). In thi…
Safety AlignmentUnraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phenomenon, dubbed as ''safety alignment deg…
Safety AlignmentAlign Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment. However, recent efforts to extend alignment to other languages often require su…