{"ID":2845614,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.03138","arxiv_id":"2511.03138","title":"DeepKnown-Guard: A Proprietary Model-Based Safety Response Framework for AI Agents","abstract":"With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety response framework designed to systematically safeguard LLMs at both the input and output levels. At the input level, the framework employs a supervised fine-tuning-based safety classification model. Through a fine-grained four-tier taxonomy (Safe, Unsafe, Conditionally Safe, Focused Attention), it performs precise risk identification and differentiated handling of user queries, significantly enhancing risk coverage and business scenario adaptability, and achieving a risk recall rate of 99.3%. At the output level, the framework integrates Retrieval-Augmented Generation (RAG) with a specifically fine-tuned interpretation model, ensuring all responses are grounded in a real-time, trustworthy knowledge base. This approach eliminates information fabrication and enables result traceability. Experimental results demonstrate that our proposed safety control model achieves a significantly higher safety score on public safety evaluation benchmarks compared to the baseline model, TinyR1-Safety-8B. Furthermore, on our proprietary high-risk test set, the framework's components attained a perfect 100% safety score, validating their exceptional protective capabilities in complex risk scenarios. This research provides an effective engineering pathway for building high-security, high-trust LLM applications.","short_abstract":"With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety response framework designed to systematically safeguard LLMs at both the input...","url_abs":"https://arxiv.org/abs/2511.03138","url_pdf":"https://arxiv.org/pdf/2511.03138v4","authors":"[\"Qi Li\",\"Jianjun Xu\",\"Pingtao Wei\",\"Jiu Li\",\"Peiqiang Zhao\",\"Jiwei Shi\",\"Xuan Zhang\",\"Yanhui Yang\",\"Xiaodong Hui\",\"Peng Xu\",\"Wenqin Shao\"]","published":"2025-11-05T03:04:35Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}