用语言模型监督视觉模型，防止多模态安全漏洞
VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap
- 在推理时利用语言模型的安全部分指导视觉模型
- 在三个恶意指令测试中显著提升安全性
- 适合关注多模态模型安全性的研究者与开发者
视觉语言模型（VLMs）因多模态融合带来新的安全风险。尽管其基于的语言模型具备文本安全对齐能力，但视觉模态的引入会破坏这一对齐。我们将其归因于模态间隙——图像与文本在共享表征空间中的分离，导致有害与无害查询的区分度降低。为此，提出 VLM-Guard，一种推理时干预策略：利用已对齐的语言模型提取安全引导方向，将视觉语言模型的表征投影至与其正交的子空间。在三个恶意指令设置下的实验表明，VLM-Guard 能有效缓解安全衰减，填补 VLM 与其语言组件间的安全对齐差距。
原文摘要 · Abstract (English)
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 safety alignment, it is easily undermined when the vision modality is integrated. We attribute this safety challenge to the modality gap, a separation of image and text in the shared representation space, which blurs the distinction between harmful and harmless queries that is evident in LLMs but weakened in VLMs. To avoid safety decay and fulfill the safety alignment gap, we propose VLM-Guard, an inference-time intervention strategy that leverages the LLM component of a VLM as supervision for the safety alignment of the VLM. VLM-Guard projects the representations of VLM into the subspace that is orthogonal to the safety steering direction that is extracted from the safety-aligned LLM. Experimental results on three malicious instruction settings show the effectiveness of VLM-Guard in safeguarding VLM and fulfilling the safety alignment gap between VLM and its LLM component.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。