Hybrid Deep Learning for Anomaly Detection in FANETs: A Defense Against DDoS Attacks
Keywords:
FANET, DDoS Detection, Anomaly Detection, ns-3 Simulation, Cybersecurity, Traffic monitoring, Autoencoder, LSTM, Network Security.Abstract
Flying ad-hoc networks (FANETs) have become indispensable in surveillance, disaster management, and environmental monitoring. The decentralized and dynamic characteristics of these systems make them vulnerable to substantial cybersecurity threats, namely distributed Denial of Service (DDoS) attacks, which can cause significant disruptions in vital activities. Here, we present VLDD-FANET (VAE-LSTM for DDoS Detection in FANETs), a novel framework designed to identify anomalies in FANETs. The system employs a robust integration of Variational Autoencoder (VAE) and Long Short-Term Memory (LSTM) networks to detect and prevent DDoS assaults in FANET traffic monitoring. A widely recognized method for modelling realistic networks, NS-3 simulation, was used to generate the dataset for this work. We employ sophisticated feature engineering techniques to measure essential network parameters, including packet rate, byte rate, flow duration, and number of communications. Identity of DDoS assaults can be achieved via detection of temporal and statistical irregularities in network traffic patterns. The suggested VLDD-FANET model exhibits exceptional performance with 0.9930 accuracy. It surpasses popular models such as LSTM, autoencoder, LSTM autoencoder, and ARIMA in performance. Through real-time detection of anomalies in FANET traffic monitoring software, our method improves FANET security against DDoS attacks. The VLDD-FANET methodology is a scalable approach to maintaining FANET integrity and functionality.
Downloads
References
John Smith and Jane Doe. Fanets: Applications and challenges. Journal of Wireless Networks, 10(2):123–134, 2021.
Alice Johnson and Robert Lee. Uavs in modern communication: A comparative study. International Journal of Communication Systems, 12(4): 215–230, 2020.
Michael Li and Emily Wong. Ddos attacks and their impact on traffic monitoring systems in fanets. IEEE Transactions on Vehicular Technology, 68(5):4123–4135, 2019.
Said Neciri, Noureddine Chaib, and Chabane Djeddi. Supervised machine learning for detecting drop attack in uav ad-hoc network. In International Conference on Emerging Intelligent Systems for Sustainable Development (ICEIS 2024), pages 286–297. Atlantis Press, 2024.
David Nguyen and Tom Brown. Statistical analysis for anomaly detection in fanets. Journal of Network Security, 18(3):102–115, 2020.
Kai Zhang and Sarah Green. Machine learning approaches in resourceconstrained fanet environments. International Journal of Machine Learning Applications, 9(1):54–67, 2019.
Dongjin Li, Dongxiao Chen, Bo Jin, Leyi Shi, Jonathan Goh, and SeeKiong Ng. Mad-gan: Multivariate anomaly detection for time series data with generative adversarial networks. In Proceedings of the 2019 Workshop on Artificial Intelligence and Security, pages 1–6, 2019.
Xiaojun Sun, Wei Liu, and Hao Zhang. Real-time anomaly detection in iot systems using deep learning models. IEEE Internet of Things Journal, 8 (7):5115–5126, 2021.
Mark Kim and Kevin White. Advanced feature engineering for ddos detection in fanets. Journal of Advanced Networking and Applications, 14(2): 201–217, 2021.
John Lee and Robert Smith. Arima-based anomaly detection in fanet traffic. Journal of Network Security, 12(4):203–210, 2020.
Michael Tan and Angela Wong. Application of arima models for anomaly detection in uav networks. In Proceedings of the International Conference on Unmanned Systems (ICUS), pages 100–107. IEEE, 2018.
Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735–1780, 1997.
Samuel Park and David Kim. Lstm-based anomaly detection in fanets for real-time network monitoring. In Proceedings of the 2018 International Conference on Wireless Communications and Network Security, pages 150– 157. IEEE, 2018.
Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning. MIT Press, Cambridge, MA, 2016.
Kevin Yu, Mark Li, and Xiaoming Wang. Resource allocation in fanets using deep reinforcement learning. IEEE Transactions on Vehicular Technology, 68(8):7253–7264, 2019.
Jinwon An and Sungzoon Cho. Variational autoencoder based anomaly detection using reconstruction probability. In Proceedings of the Machine Learning for Sensory Data Analysis (MLSDA), pages 1–6, 2015.
Diederik P Kingma and Max Welling. An introduction to variational autoencoders. Foundations and Trends in Machine Learning, 12(4):307–392, 2019.
Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. Stochastic backpropagation and approximate inference in deep generative models. In Proceedings of the 31st International Conference on Machine Learning (ICML), pages 1278–1286, 2014.
Haowen Xu, Yue Chen, Jie Zhao, Feng Li, and Heng Huang. Unsupervised anomaly detection via variational auto-encoder for seasonal kpis in web applications. In Proceedings of the 2018 World Wide Web Conference (WWW), pages 187–196. International World Wide Web Conferences Steering Committee, 2018.
Xinyi Chen and Xiaolong Zhang. Autoencoder-based network anomaly detection for cybersecurity. IEEE Transactions on Cybernetics, 50(3):972–983, 2020.
Haoyong Choi, Hyojung Lim, Youngsun Kim, and Seungmin Cho. Ganbased anomaly detection in imbalanced datasets. IEEE Access, 7:60706– 60716, 2019.
Jianlong Xie, Ross Girshick, and Ali Farhadi. Unsupervised deep embedding for clustering analysis. In Proceedings of the 33rd International Conference on Machine Learning (ICML), pages 478–487. ACM, 2016.
Jian Wang, Ming Liu, and Hui Zhang. Feature selection for anomaly detection in network traffic using autoencoders. IEEE Transactions on Network and Service Management, 18(2):1123–1134, 2021.
Mikhail Kuznetsov, Dmitry Kharitonov, Vladislav Marchenkov, and Dmitry Skobeltsyn. Feature selection for anomaly detection in industrial control systems. In Proceedings of the 2018 International Conference on Industrial Internet (ICII), pages 121–126. IEEE, 2018.
Wei Li, Li Zhang, and Xin Wang. Feature selection methods for anomaly detection in industrial control systems. IEEE Access, 7:88350–88361, 2019.
Shyam Madan, Rahul Sharma, and Ankit Gupta. A hybrid model for network anomaly detection using machine learning techniques. Journal of Network and Computer Applications, 185:103078, 2021.
Hong Zhou, Min Li, and Tao Yang. A hybrid deep learning model for anomaly detection in smart grid systems. IEEE Transactions on Smart Grid, 11(3):1795–1805, 2020.
Rajesh Mishra, Neeraj Gupta, and Vinod Prasad. Ddos attack detection using machine learning in sdn-based iot networks. Journal of Network and Computer Applications, 185:103076, 2021.
Syed A. Raza. Feature extraction for anomaly detection in network traffic. Journal of Network and Computer Applications, 189:103219, 2022.
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(10):2235–2249, 2018.
Diederik P Kingma and Max Welling. Auto-encoding variational bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR), 2014.
Downloads
Published
How to Cite
Issue
Section
License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.