A Cybersecurity MLPS Large Language Model with Multi-Path Retrieval Fusion
2026-07-27 • Cryptography and Security
Cryptography and Security
AI summaryⓘ
The authors studied how to better analyze China's Multi-Level Protection Scheme (MLPS), a key cybersecurity framework. They found that current methods, which are mostly manual or rule-based, struggle with complex situations. To improve this, they created a special large language model that uses different ways to find relevant information more accurately. Their approach also includes a new way to score how well the model answers MLPS-related questions. Tests showed their method gave more precise and reliable results.
Multi-Level Protection Scheme (MLPS)cybersecurity standardslarge language modelshierarchical retrievalrule-based analysisquestion answeringclause accuracytraceabilityevaluation metricstokenization
Authors
Qian Li, Zhenyan Qi, Liang Shen, Yuan Zhang, Yifan Wan, Junyuan Ma, Yining Hu
Abstract
The Multi-Level Protection Scheme (MLPS) is a foundational system in China's cybersecurity governance framework. Therefore, accurate analysis and understanding of MLPS requirements are essential. At present, MLPS analysis still relies mainly on manual interpretation of standards and rule-based tools. This makes it hard to provide stable and consistent compliance analysis in complex application scenarios. The rise of large language models has created new opportunities for making MLPS work more intelligent. However, in standards-intensive and security-sensitive scenarios, general-purpose large language models often cannot ensure controllable reasoning or complete understanding of rules. This paper proposes a large language model framework for MLPS that integrates multiple retrieval strategies. It combines hierarchical retrieval, tree-based retrieval, and tokenization-based matching retrieval. This design helps maintain retrieval coverage while reducing the interference of irrelevant context in the reasoning process. To address the requirements of MLPS question answering for clause accuracy, conclusion traceability, and practical deployability, this paper adopts a evaluation method based on multi-dimensional weighted scoring to quantitatively assess model responses. In comparative experiments on ten typical questions, the proposed domain-specific large language model for MLPS achieved higher overall scores.