loading page

An ADS-B Signal Poisoning Method based on U-Net
  • +1
  • Tianhao Wu,
  • Shunjie Zhang,
  • Jungang Yang,
  • Pengfei Lei
Tianhao Wu
National University of Defense Technology College of Electronic Science and Technology

Corresponding Author:wutianhao16@nudt.edu.cn

Author Profile
Shunjie Zhang
National University of Defense Technology College of Electronic Science and Technology
Author Profile
Jungang Yang
National University of Defense Technology
Author Profile
Pengfei Lei
Air Force Engineering University
Author Profile

Abstract

Automatic dependent surveillance-broadcast (ADS-B) has been widely used due to its low cost and high precision. The deep learning methods for ADS-B signal classification have achieved a high performance. However, recent studies have shown that deep learning networks are very sensitive and vulnerable to small noise. We propose an ADS-B signal poisoning method based on U-Net. This method can generate poisoned signals. We assign one of ADS-B signal classification networks as the attacked network and another one as the protected network. When poisoned signals are fed into these two well-performed classification networks, the poisoned signal will recognized incorrectly by the attacked network while classified correctly by the protected network. We further propose an Attack-Protect-Similar loss to achieve “triple-win” in leading attacked network poor performance, protected network well performance and the poisoned signals similar to unpoisoned signals. Experimental results show attacked network classifies poisoned signals with a 1.55% classification accuracy, while the protected network classifies rate is still maintained at 99.38%.
11 Sep 2022Submitted to Electronics Letters
13 Sep 2022Submission Checks Completed
13 Sep 2022Assigned to Editor
25 Sep 2022Reviewer(s) Assigned
10 Oct 2022Review(s) Completed, Editorial Evaluation Pending
13 Oct 2022Editorial Decision: Revise Minor
14 Oct 20221st Revision Received
14 Oct 2022Submission Checks Completed
14 Oct 2022Assigned to Editor
14 Oct 2022Review(s) Completed, Editorial Evaluation Pending
14 Oct 2022Reviewer(s) Assigned
18 Nov 2022Editorial Decision: Accept