My research interests lie in the security and robustness of over-the-air (OtA) computation, particularly for secure data aggregation in distributed wireless systems. Inspired by applications such as sensor networks and federated learning, I study how wireless channels can be leveraged to aggregate data efficiently while remaining resilient to security threats and practical impairments. This includes investigating protection against eavesdropping, mitigation of malicious jamming, and the broader robustness of OtA schemes. The overarching goal is to develop reliable and secure communication mechanisms for future distributed intelligence systems.
David Nordlund
PhD student
Publications
2024
Byzantine-Resilient Hierarchical Federated Learning with Clustered Over-The-Air Aggregation
2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW 2024, p. 715-719
(Conference paper)
https://dx.doi.org/10.1109/ICASSPW62465.2024.10626690
2023
Detecting Active Attacks in Over-the-Air Computation using Dummy Samples
FIFTY-SEVENTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, IEEECONF, p. 1691-1696
(Conference paper)
https://dx.doi.org/10.1109/IEEECONF59524.2023.10476745