Proceedings of the 16th ACM Symposium on QoS and Security for Wireless and Mobile Networks 2020
DOI: 10.1145/3416013.3426446
|View full text |Cite
|
Sign up to set email alerts
|

Novelty-based Intrusion Detection of Sensor Attacks on Unmanned Aerial Vehicles

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
16
0
2

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 66 publications
(38 citation statements)
references
References 13 publications
0
16
0
2
Order By: Relevance
“…During the thresholding phase, which performs an inference, we utilized flight logs from both safe states and faulty states to measure the detection performance. The detailed description of the UA dataset is illustrated in [ 22 ].…”
Section: Proposed Methodologymentioning
confidence: 99%
See 1 more Smart Citation
“…During the thresholding phase, which performs an inference, we utilized flight logs from both safe states and faulty states to measure the detection performance. The detailed description of the UA dataset is illustrated in [ 22 ].…”
Section: Proposed Methodologymentioning
confidence: 99%
“…Still, the proposed approach highly relied on a supervised manner. Whelan et al [ 22 ] defined fault detection task as a novelty-based detection. They conducted research using various one-class classifiers, including One-class SVM (OC-SVM), Autoencoder, and Local Outlier Factor (LOF).…”
Section: Literature Reviewmentioning
confidence: 99%
“…Авторы статьи [12] предлагают анализировать журналы полета БПЛА и из них выделять признаки атаки. Причем, в отличие от предыдущих работ, они предлагают разделить признаки по отдельным категориям и для каждой категории использовать отдельную нейросеть для анализа.…”
Section: рис 1 схема влияния атаки на бпла и взаимосвязь с инцидентам...unclassified
“…The open-source UAV attack dataset is used [31], which contains a mixture of normal flights and GPS-spoofed flights for six UAV platforms. A similar process is followed relative to [11] and [12], who also perform novelty detection on this dataset. However, improvements are made, including more generalisable models across all datasets, and enhanced interpretability of predictions.…”
Section: A Overview Of Analysismentioning
confidence: 99%
“…Sufficient quantities of labelled anomalies are difficult to acquire however, and so unsupervised learning overcomes this by modelling normal behaviour to identify anomalies without the requirement for labels. This is known as novelty detection and is well-studied for UAVs, with classical-based approaches like One-Class Support Vector Machine (OC-SVM), Isolation Forest (IF) [10] and Local Outlier Factor (LOF) [11] being common. Recently, deep unsupervised learning architectures have emerged, including autoencoders for automatic UAV fault detection [12] and Long-Term Short-Term (LSTM) networks for detecting ADS-B manipulation [7].…”
Section: Introductionmentioning
confidence: 99%