Abstract: Large Language Models (LLMs), as a cornerstone technology in Natural Language Processing (NLP), have demonstrated exceptional capabilities in text generation, information retrieval, and conversational systems. These models, such as ChatGPT, LLaMA, and Gemini, have been applied across various fields, including healthcare, education, and finance, achieving near-human or even superhuman performance. However, with the widespread adoption of LLMs, their storage mechanisms face significant security and privacy risks throughout their lifecycle. Core storage modules, including model file storage, inference caching, and knowledge vector storage, support the functionality and efficiency of LLMs but also expose vulnerabilities. Model file storage faces risks such as weight leakage and backdoor injection, while inference caching is susceptible to timing, hardware, and network side-channel attacks. Additionally, knowledge vector storage faces data poisoning, backdoor embedding, and privacy leakage threats. To address these challenges, researchers have proposed defense strategies such as model encryption, backdoor detection, cache partitioning, and content filtering techniques. Despite these advances, balancing security with efficiency remains a critical challenge. This paper systematically reviews security risks and defense mechanisms for LLM storage across its lifecycle, focusing on attack surfaces and mitigation strategies. It identifies current limitations and highlights future research directions to enhance the security and reliability of LLM storage mechanisms.