LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities
LiteLMGuard: 无缝且轻量级的设备端提示过滤,用于保护小型语言模型免受量化引发的风险和漏洞
机构 * SPIES Research Lab, Dept. of CSE, Texas A&M University(SPIES研究实验室,计算机科学与工程系,德克萨斯大学阿马尔科分校)
专题命中 效率与部署 :language model(title,abstract);small language model(title,abstract);large language model(abstract);SLM(abstract)
AI总结 LiteLMGuard通过设备端实时提示过滤,有效保护小型语言模型免受量化带来的安全风险。
Comments 18 pages, 19 figures, and 3 tables