How Potent are Evasion Attacks for Poisoning Federated Learning-Based Signal Classifiers?

• Published in: ICC 2023 - IEEE International Conference on Communications pp. 2376 - 2381
• Main Authors: Wang, Su, Sahay, Rajeev, Brinton, Christopher G.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 28.05.2023
• Subjects: Adversarial attacks; automatic modulation classification; Data models; deep learning; Federated learning; Modulation; Pattern classification; Performance evaluation; Perturbation methods; privacy; security; Training

There has been recent interest in leveraging federated learning (FL) for radio signal classification tasks. In FL, model parameters are periodically communicated from participating devices, training on their own local datasets, to a central server which aggregates them into a global model. While FL...