基于人工智能的网络安全策略自学习与优化框架  

Network Security Policy Self-learning and Optimization Framework Based on Artificial Intelligence

作　　者：郭小杰 李由由 马艳芳[1] GUO Xiaojie;LI Youyou;MA Yanfang(Jiaozuo University,Jiaozuo,Henan 454000,China)

机构地区：[1]焦作大学,河南焦作454000

出　　处：《移动信息》2024年第12期183-185,共3页Mobile Information

摘　　要：文中提出了一种基于人工智能的网络安全策略自学习与优化框架。该框架通过模块化、可扩展性和自适应性的设计原则,构建了一个包含数据收集、自学习、策略优化和执行4个层次的闭环系统。利用机器学习和深度学习技术,该框架能实时地检测网络威胁,并通过强化学习、遗传算法等优化技术,对现有安全策略进行动态调整和优化。文中还探讨了多目标优化策略、实时反馈与动态调整策略以及协同进化策略在网络安全策略优化中的应用。综合应用这些策略,能显著提高网络系统的安全性和稳健性,为应对不断变化的网络威胁提供一种有效的解决方案。This paper proposes an artificial intelligence-based network security policy self-learning and optimization framework.The framework constructs a closed-loop system with four levels of data collection,self-learning,strategy optimization and execution through the design principles of modularity,scalability and adaptability.Using machine learning and deep learning technologies,the framework can detect network threats in real time and dynamically adjust and optimize existing security policies through optimization techniques such as reinforcement learning and genetic algorithms.This paper also discusses the application of multiobjective optimization strategy,real-time feedback and dynamic adjustment strategy and co-evolution strategy in network security strategy optimization.Through the comprehensive application of these strategies,the security and robustness of the network system can be significantly improved,and an effective solution can be provided to deal with the ever-changing network threats.

关 键 词：人工智能 网络安全策略 自学习 优化框架 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]