SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypots
SBASH:用于设计和评估RAG与提示调优的LLM蜜罐框架
机构 * University of California, Berkeley(加州大学伯克利分校)
专题命中 效率与部署 :LLM(title,title_cn);large language model(abstract,comments);language model(abstract,comments);分类 cs.CL、cs.LG
AI总结 提出SBASH框架,利用轻量级本地LLM和RAG技术构建蜜罐,通过多种指标评估RAG与提示调优对LLM蜜罐真实性和响应延迟的影响。
Comments to be published in: The 3rd International Conference on Foundation and Large Language Models (FLLM2025), IEEE, 2025
Journal ref 2025 3rd International Conference on Foundation and Large Language Models (FLLM), IEEE, 2025