2020
DOI: 10.1186/s13638-020-01756-8
|View full text |Cite
|
Sign up to set email alerts
|

ADS-B spoofing attack detection method based on LSTM

Abstract: The open and shared nature of the Automatic Dependent Surveillance Broadcast (ADS-B) protocol makes its messages extremely vulnerable to various security threats, such as jamming, modification, and injection. This paper proposes a long short-term memory (LSTM)-based ADS-B spoofing attack detection method from the perspective of data. First, the message sequence is preprocessed in the form of a sliding window, and then, an LSTM network is used to perform prediction training on the windows. Finally, the residual… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
13
0
1

Year Published

2021
2021
2025
2025

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 26 publications
(14 citation statements)
references
References 27 publications
0
13
0
1
Order By: Relevance
“…The authors train the model on a dataset generated with the help of OpenSky. From the perspective of ADS-B messages, a spoofing a ack detection technique based on LSTM is proposed [89]. In this research paper, the author focused on three different ADS-B a acks: injection, jamming, and modification.…”
Section: Machine Learning-based Security Solutionsmentioning
confidence: 99%
See 1 more Smart Citation
“…The authors train the model on a dataset generated with the help of OpenSky. From the perspective of ADS-B messages, a spoofing a ack detection technique based on LSTM is proposed [89]. In this research paper, the author focused on three different ADS-B a acks: injection, jamming, and modification.…”
Section: Machine Learning-based Security Solutionsmentioning
confidence: 99%
“…In this research paper, the author focused on three different ADS-B a acks: injection, jamming, and modification. The flowchart of the proposed technique is shown in Figure 13 [89]. Based on the sliding window, the ADS-B messages sequence is pre-processed and implemented in the LSTM network model with 93% accuracy [89].…”
Section: Machine Learning-based Security Solutionsmentioning
confidence: 99%
“…Attacks on the ADS-B, which can have different levels of impact on aircraft systems, include eavesdropping, jamming, message insertion, message deletion, and message modification (Table 1) (Wang et al, 2020).…”
Section: Cyber Attacks On the Ads-bmentioning
confidence: 99%
“…Factors such as the number and density of targets, target dynamic characteristics, sensor performance, noise and interference sources, and filter performance selected for state estimation all have an impact on the performance of the multitarget tracking system. With the development of multitarget tracking systems, such as multisource information fusion theory [6], nonlinear filtering theory [7], random finite set theory [8], and other new technologies, the performance of the multitarget tracking system has significantly improved the performance of the multitarget tracking system. Target uncertainty and observation uncertainty are two important issues that need to be resolved in a multitarget tracking system.…”
Section: Related Workmentioning
confidence: 99%