Multimodal large language models (MLLMs) have shown impressive reasoning abilities, which, however, are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting unsafe responses, we observe that safety mechanisms of the pre-aligned LLMs in MLLMs can be easily bypassed due to 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 intrinsic safety mechanism of pre-aligned LLMs in MLLMs. Experiments on five state-of-the-art (SoTA) MLLMs demonstrate that our ECSO enhances model safety significantly (e.g., a 37.6% improvement on the MM-SafetyBench (SD+OCR), and 71.3% on VLSafe for the 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.

翻译：多模态大语言模型（MLLMs）展现了强大的推理能力，但相较于其前身大语言模型（LLMs），它们更容易受到越狱攻击。尽管仍能检测不安全响应，但本研究发现，由于图像特征的引入，MLLMs中预对齐LLMs的安全机制容易被绕过。为构建鲁棒的MLLMs，我们提出ECSO（闭目即安）——一种无需训练的新颖保护方法。该方法利用MLLMs固有的安全感知能力，通过自适应地将不安全图像转换为文本，激活MLLMs中预对齐LLMs的内在安全机制，从而生成更安全的响应。在五个最先进（SoTA）MLLMs上的实验表明，我们的ECSO显著提升了模型安全性（例如，在MM-SafetyBench（SD+OCR）上对LLaVA-1.5-7B提升37.6%，在VLSafe上提升71.3%），同时保持其在常见MLLM基准测试中的实用性能。此外，我们证明ECSO可用作数据引擎，无需额外人工干预即可生成用于MLLM对齐的监督微调（SFT）数据。