基于深度学习的ADS-B异常数据检测模型  

ADS-B anomaly data detection model based on deep learning

作　　者：丁建立[1,2] 邹云开 王静 王怀超[1] DING Jianli;ZOU Yunkai;WANG Jing;WANG Huaichao(College of Computer Science and Technology,Civil Aviation University of China,Tianjin 300300,China;Sino-European Institute of Aviation Engineering,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学计算机学院,天津300300 [2]中国民航大学中欧航空工程师学院,天津300300

出　　处：《航空学报》2019年第12期162-172,共11页Acta Aeronautica et Astronautica Sinica

基　　金：国家自然科学基金民航联合基金(U1833114);民航安全能力项目(AADSA0018)~~

摘　　要：广播式自动相关监视(ADS-B)是下一代空中交通运输系统的重要组成部分,是新航行系统中非常重要的通信和监视技术,但其协议没有提供相关的信息认证和数据加密,因此极其容易受到欺骗干扰的影响。针对ADS-B报文数据特点,采用深度学习的seq2seq模型对ADS-B报文数据进行重构,通过重构误差来检测异常,并对数据进行特征扩展,使模型能更好的捕捉数据的时间依赖性。实验结果表明,所采用的方法优于传统的机器学习方法,且在数据特征扩展后,模型检测效果提升。相比于现有的欺骗干扰检测方法,该方法不需要改变ADS-B系统的协议,也不需要额外的节点或传感器参与,具有一定的适应性和灵活性。Automatic Dependent Surveillance-Broadcast(ADS-B)is an important part of the next generation air transportation system.It is a critical communication and monitoring technology in the new navigation system,but its protocol does not provide relevant authentication and data encryption,so it is extremely vulnerable to various spoofing attack.Based on the data characteristics,this paper uses the deep learning seq2 seq model to reconstruct the ADS-B time series,and the reconstruction error can detect the anomalous ADS-B messages.Extending the feature space of time series enables the model to better capture the time dependence to further improve the effect of anomaly detection.The experimental results show that the proposed method is superior to traditional machine learning methods and time series enrichment can improve detection results.Compared with the existing spoofing attack detection method,the proposed method does not need to change the ADS-B protocol and does not require additional participating nodes or sensors,and has certain adaptability and flexibility.

关 键 词：广播式自动相关监视(ADS-B) 安全性 异常检测 深度学习 seq2seq模型 

分 类 号：V243[航空宇航科学与技术—飞行器设计] TP277[自动化与计算机技术—检测技术与自动化装置]