# DeepKnown-Guard: A Proprietary Model-Based Safety Response Framework for AI Agents

arXiv: https://arxiv.org/abs/2511.03138 · HTML: https://mlsanity.com/paper/2511.03138/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 15 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 12 of 12)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety](https://mlsanity.com/paper/2505.20065/) (2025)
- [S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models](https://mlsanity.com/paper/2405.14191/) (2024)
- [Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training](https://mlsanity.com/paper/2508.14904/) (2025)

## Built on by (most cited first, 2 of 2)

- [A Comparative Evaluation of AI Agent Security Guardrails](https://mlsanity.com/paper/2604.24826/) (2026)
- [Grading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning](https://mlsanity.com/paper/2608.19009/) (2026)

## Abstract (arXiv)

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.