Logo image
Federated Learning-enabled Network Incident Anomaly Detection Optimization for Drone Swarms
Conference proceeding   Open access

Federated Learning-enabled Network Incident Anomaly Detection Optimization for Drone Swarms

Kevin Kostage, Rohan Adepu, Jenaya Monroe, Trevontae Haughton, Juan Mogollon, Saketh Poduvu, Kannappan Palaniappan, Chengyi Qu, Prasad Calyam and Reshmi Mitra
Proceedings of the 26th International Conference on Distributed Computing and Networking, pp.104-114
ACM Other Conferences
ICDCN 2025: 26th International Conference on Distributed Computing and Networking
01-04-2025

Abstract

Security and privacy -- Intrusion detection systems Security and privacy -- Mobile and wireless security
The increasing reliance on drone swarms for various applications necessitates robust real time anomaly detection mechanisms to ensure operational security and efficiency. Federated learning is particularly well-suited in the drone context as it enables decentralized data processing, preserving data privacy and security while enhancing detection accuracy. In this paper, we explore optimization methods for federated learning-enabled network incident anomaly detection in drone swarms using the NSF AERPAW platform. To achieve this, we demonstrate a defense mechanisms such as differential privacy and adversarial training, to strengthen the robustness of federated learning models against data poisoning attacks. We are collecting three sets of metrics for accuracy, system and network usage under a variety of test cases reflecting benign, mildly poisoned, highly malicious, safe situations. The experimental results reveal that adversarial training is particularly effective, achieving up to 91.1% accuracy with a 33% data poisoning volume. Additionally, we evaluate the computational overhead introduced by these defenses, finding that while they enhance security, they also increase CPU usage by up to 233% in active drone scenarios. These findings highlight the trade-offs between security and operational efficiency in FL-enabled drone swarms, offering critical insights for deploying robust, real-time anomaly detection systems in decentralized environments.
url
https://doi.org/10.1145/3700838.3700857View
Published (Version of record) Open

Related links

Metrics

22 Record Views
3 Times Cited - Scopus

Details

Logo image