Luo Peng, Wang Buhong, Tian Jiwei, Liu Chao, Yang Yong
School of Information and Navigation, Air Force Engineering University, Xi'an 710051, China.
Sensors (Basel). 2024 Jun 2;24(11):3584. doi: 10.3390/s24113584.
Deep learning has shown significant advantages in Automatic Dependent Surveillance-Broadcast (ADS-B) anomaly detection, but it is known for its susceptibility to adversarial examples which make anomaly detection models non-robust. In this study, we propose ime eighborhood ccumulation teration ast radient ign ethod () adversarial attacks which fully take into account the temporal correlation of an ADS-B time series, stabilize the update directions of adversarial samples, and escape from poor local optimum during the process of iterating. The experimental results show that TNAI-FGSM adversarial attacks can successfully attack ADS-B anomaly detection models and improve the transferability of ADS-B adversarial examples. Moreover, the TNAI-FGSM is superior to two well-known adversarial attacks called the Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM). To the best of our understanding, we demonstrate, for the first time, the vulnerability of deep-learning-based ADS-B time series unsupervised anomaly detection models to adversarial examples, which is a crucial step in safety-critical and cost-critical Air Traffic Management (ATM).
深度学习在自动相关监视广播（ADS-B）异常检测中显示出显著优势，但它以易受对抗样本影响而闻名，这使得异常检测模型缺乏鲁棒性。在本研究中，我们提出了 ime 邻域累积迭代快速梯度符号方法（TNAI-FGSM）对抗攻击，该方法充分考虑了ADS-B时间序列的时间相关性，稳定了对抗样本的更新方向，并在迭代过程中逃离不良局部最优。实验结果表明，TNAI-FGSM对抗攻击能够成功攻击ADS-B异常检测模型，并提高ADS-B对抗样本的可转移性。此外，TNAI-FGSM优于两种著名的对抗攻击方法，即快速梯度符号方法（FGSM）和基本迭代方法（BIM）。据我们所知，我们首次证明了基于深度学习的ADS-B时间序列无监督异常检测模型对对抗样本的脆弱性，这是安全关键和成本关键的空中交通管理（ATM）中的关键一步。
