用合成嵌入提升多模态模型安全，仅靠文本就能实现
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings
- 通过梯度优化生成额外模态的合成嵌入，扩展文本数据
- 单张RTX3090显卡24秒内生成高质量嵌入，显著提升安全防护
- 适用于资源受限场景，尤其适合缺乏多模态数据的研究者
多模态大语言模型（MLLMs）存在严重安全漏洞。尽管使用包含文本和额外模态的数据集进行安全对齐能有效增强安全性，但构建此类数据集成本高昂。现有低资源安全对齐方法（如纯文本对齐）在应对额外模态带来的安全风险时表现不佳。为此，我们提出合成嵌入增强的安全对齐方法（SEA），通过梯度更新优化额外模态的嵌入，以扩展文本数据集。该方法使仅拥有文本数据时也能实现多模态安全对齐训练。在基于图像、视频和音频的MLLM上进行的大量实验表明，SEA可在单张RTX3090 GPU上24秒内生成高质量嵌入，显著提升模型面对额外模态威胁时的安全性。为评估视频与音频引入的安全风险，我们还构建了新基准VA-SafetyBench，多个MLLM在该基准上均表现出高攻击成功率，验证其挑战性。代码与数据将开源于https://github.com/ZeroNLP/SEA。
原文摘要 · Abstract (English)
Multimodal Large Language Models (MLLMs) have serious security vulnerabilities.While safety alignment using multimodal datasets consisting of text and data of additional modalities can effectively enhance MLLM's security, it is costly to construct these datasets. Existing low-resource security alignment methods, including textual alignment, have been found to struggle with the security risks posed by additional modalities. To address this, we propose Synthetic Embedding augmented safety Alignment (SEA), which optimizes embeddings of additional modality through gradient updates to expand textual datasets. This enables multimodal safety alignment training even when only textual data is available. Extensive experiments on image, video, and audio-based MLLMs demonstrate that SEA can synthesize a high-quality embedding on a single RTX3090 GPU within 24 seconds. SEA significantly improves the security of MLLMs when faced with threats from additional modalities. To assess the security risks introduced by video and audio, we also introduced a new benchmark called VA-SafetyBench. High attack success rates across multiple MLLMs validate its challenge. Our code and data will be available at https://github.com/ZeroNLP/SEA.
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。