基于改进BiLSTM的ADS-B信号欺骗检测方法研究  

Study on Deception Detection Dethod for ADS-B Signals Based on Improved BiLSTM

作　　者：颜丽蓉 赵泽荣[1] YAN Lirong;ZHAO Zerong(Civil Aviation Flight University of China,Guanghan 618300,China)

机构地区：[1]中国民用航空飞行学院,四川广汉618300

出　　处：《计算机测量与控制》2025年第3期54-62,共9页Computer Measurement &Control

基　　金：民航安全能力SA项目(ASSA2024/101);中央高效基本科研业务费专项资金资助项目(24CAFUC03071)。

摘　　要：随着智能交通系统的快速发展,ADS-B技术作为一种先进的空中交通管理监控手段得到了广泛应用;然而,ADS-B信号的开放性和易受攻击性使其成为潜在的欺骗攻击目标;为提升飞行安全并防止ADS-B系统遭受欺骗干扰,提出了一种基于深度学习的全向信标信号处理方法,用于检测ADS-B信号中的欺骗行为;该方法利用全向信标收集ADS-B信号数据并提取相关特征,随后通过BiLSTM深度学习模型对特征进行训练,实现在正常信号与欺骗信号之间的有效区分;结合焦点损失函数和贝叶斯优化算法对信号检测方法进行优化,并通过几何位置相关函数量化飞行状态误差;结果表明,模型的训练损失值和训练准确率分别达到了0.25和98.15%,改进后的BiLSTM模型在分类性能上所有指标均超过了99.50%;此外,研究方法在飞行速度、水平飞行方向和垂直飞行方向的检测误差分别仅为0.01%、0.01%和0.04%;对真实信号的检测显示,其飞行速度、水平和垂直方向的损失值均为1,而欺骗信号在这些指标上的损失值误差分别为15%、1%和0.3%;综上所述,面向全向信标信号处理的深度学习ADS-B信号欺骗检测方法研究,有效实现了优异的检测准确率和鲁棒性,为民用航空安全领域提供了重要的技术支持与参考。With the rapid development of intelligent transportation systems,automatic dependent surveillance-broadcast(ADS-B)technology,as an advanced means of air traffic management and monitoring,is widely applied.However,the openness and vulnerability of ADS-B signals make it a potential target for deception attacks.In order to improve flight safety and prevent interference and deception,a deep learning based omnidirectional beacon signal processing method is proposed,which detects deception behavior in ADS-B signals.This method uses omnidirectional beacons to collect ADS-B signals and extract relevant features,and then trains the features through a bidirectional long short-term memory(BiLSTM)deep learning model to effectively distinguish between normal signals and deceptive signals.Optimize signal detection method by combining focus loss function and Bayesian optimization algorithm,and quantify flight state error through geometric position correlation function.The results show that the loss value and accuracy of the model training reach up to 0.25 and 98.15%,respectively.all indicators of the improved BiLSTM model are over 99.50%in the classification performance.In addition,the detection errors of the research method in flight speed,horizontal flight direction,and vertical flight direction are only 0.01%,0.01%,and 0.04%,respectively.The detection of real signals shows that the loss values of flight speed,horizontal and vertical directions are all 1,while the loss errors of deception signals on these indicators are 15%,1%and 0.3%,respectively.In summary,deep learning ADS-B signal deception detection methods for omnidirectional beacon signal processing effectively achieve high-quality detection accuracy and robustness,providing important technical support and reference for civil aviation safety.

关 键 词：全向信标 ADS.B 信号欺骗检测 深度学习 BiLSTM 

分 类 号：TP355.1[自动化与计算机技术—计算机系统结构]