| 摘要: |
| 无线通信对抗中未经授权的非协作攻击信号为5G通信系统安全带来了巨大的风险挑战。结合无线攻击信号响应速度快的特点、非协作通信缺乏先验信息的固有缺陷以及5G通信系统对信号质量的严格要求，迫切需要一种攻击识别能力和抗复杂电磁环境能力更强的5G攻击信号识别方法。本文从信号角度对多层次的5G攻击信号展开参数估计和盲识别，构建了一个系统化、可演进的非协作5G攻击信号安全识别体系。首先研究5G攻击信号样本库构建和自动匹配识别技术，引入一种可行方向策略的序列最小优化算法，构建自下而上的多层次特征分类器。构造攻击信号可分辨、易测量且稳定的特征参数组，充分利用攻击类型的先验信息和前期安全监测结果实现快速匹配识别和安全研判，通过三元组形式构建5G信号安全威胁库中的知识图谱。其次，在攻击样本库失效的条件下，研究5G攻击信号的盲识别与参数估计技术，创新性地提出一套闭环的攻击参数估计与攻击盲识别的反馈迭代处理框架，通过判决反馈辅助特征参数修正和攻击参数判断，构造决策树逐级确定攻击类型，提高5G攻击信号的识别能力。不同于追求高精度的通用信号识别方法，本文尝试从安全性的角度识别攻击信号，以确保复杂电磁环境下5G通信系统的正常通信和信息安全，为5G通信信号的安全监测奠定了理论和技术基础。 |
| 关键词: 非协作攻击 5G通信系统 攻击检测 特征参数估计 |
| DOI：10.19363/J.cnki.cn10-1380/tn.2024.08.06 |
| 投稿时间：2023-01-21修订日期：2023-03-08 |
| 基金项目:国家重点研发计划 |
|
| An Identification System for Non-Cooperative 5G Attack Signals in Complex Electromagnetic Environment |
|
PENG Cheng, FAN Wei, HUANG Weiqing
|
| (Institute of Information Engineering, Chinese Academy of Sciences) |
| Abstract: |
| Unauthorized non-cooperative attack signals in wireless communication countermeasure bring huge risks to 5G communication system security. There is an urgent need for a 5G attack signal identification method, which has stronger ability to identify attack and resist complex environment based on the wireless attack signals of high-speed, inherent defect of non-cooperative communication lacking prior information and strict requirements for signal quality of 5G communication system. Based on parameter estimation and blind identification of mul-ti-level 5G attack signals from the perspective of signals, this paper constructs a systematic and evolvable security identification system for non-cooperative 5G attack signals. Firstly, the paper takes analysis of 5G attack signals sample library construction and automatic matching and identification technology, and introduces a sequence minimum optimization algorithm of feasible direction strategy and construct a bottom-up multi-level feature classi-fier. Constructing a resolvable, easily measured and stable characteristic parameter group of attack signals to fully utilize the prior information of attack types and preliminary security monitoring results, in order to achieve rapid matching identification and security research and judgment. The knowledge map in the 5G attack signal security threat library is constructed in the form of triplets. Then, under the condition of attack sample library failure, this paper studies the blind identification and parameter estimation of 5G attack signals. A feedback iterative processing framework for closed-loop attack parameter estimation and blind attack identification is innovatively proposed. The decision feedback is used to assist feature parameter correction and attack parameter judgment, and a decision tree is constructed to determine the attack type level by level, so as to improve the ability of 5G attack signal identi-fication. Different from the general signal identification method that pursues high accuracy, this paper attempts to identify attack signals from the perspective of security, to ensure normal communication and information security of 5G communication system under complex electromagnetic environment, thus lays a theoretical and technical foundation for security monitoring of 5G communication signals. |
| Key words: non-cooperative attack 5G communication system attack detection parameter estimation |
