1. NCCU Academic Hub
  2. Publications
  3. College of Informatics
  4. Proceedings
  5. Item

Publications-Proceedings

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 Mitigating Jamming Attacks in Over-the-Air Federated Learning via Coordinated Dropout
作者 孫士勝
Ezawa, Shuto, Nishimoto, Kenji;Chiang, Yi-Han;Sun, Shi-Sheng;Chiang, Tsung-Wei;Lin, Hai;Ji, Yusheng
貢獻者 資訊系
關鍵詞 Federated learning; over-the-air computation; jamming attacks; dropout; Artificial Intelligence of Things
日期 2025-12
上傳時間 7-May-2026 16:22:35 (UTC+8)
摘要 The over-the-air (OTA) computation which utilizes the waveform-superposition property of wireless signals has been considered as a promising approach to simultaneously accomplish communication and computing tasks in multiple access channels. Equipping federated learning (FL) with the OTA computation allows distributed Artificial Intelligence of Things (AIoT) devices to collaboratively train machine learning models over wireless environment, while preserving data privacy without excessive bandwidth consumption. In fact, the appearance of jamming attacks in OTA-FL systems can severely disrupt the convergence. This paper studies the problem of jamming attacks and its countermeasures in over-the-air federated learning (OTA-FL). To this end, we propose the coordinated dropout strategy (CoDrop), which enables AIoT devices to collaboratively drop out (i.e., to refrain from transmitting) part of their gradients so that the jamming signals aggregated in received signals can be accurately measured and mitigated. Our simulation results reveal that CoDrop is effective in alleviating the negative impacts of jamming signals with significantly low dropout rates, and it is shown to converge well as compared to existing solutions under various parameter settings.
關聯 2025 IEEE Global Communications Conference (GLOBECOM) Proceedings, IEEE Communications Society, pp.3958-3963
資料類型 conference
DOI https://doi.org/10.1109/GLOBECOM59602.2025.11432204
dc.contributor 資訊系
dc.creator (作者) 孫士勝
dc.creator (作者) Ezawa, Shuto, Nishimoto, Kenji;Chiang, Yi-Han;Sun, Shi-Sheng;Chiang, Tsung-Wei;Lin, Hai;Ji, Yusheng
dc.date (日期) 2025-12
dc.date.accessioned 7-May-2026 16:22:35 (UTC+8)-
dc.date.available 7-May-2026 16:22:35 (UTC+8)-
dc.date.issued (上傳時間) 7-May-2026 16:22:35 (UTC+8)-
dc.identifier.uri (URI) https://ah.lib.nccu.edu.tw/item?item_id=182385-
dc.description.abstract (摘要) The over-the-air (OTA) computation which utilizes the waveform-superposition property of wireless signals has been considered as a promising approach to simultaneously accomplish communication and computing tasks in multiple access channels. Equipping federated learning (FL) with the OTA computation allows distributed Artificial Intelligence of Things (AIoT) devices to collaboratively train machine learning models over wireless environment, while preserving data privacy without excessive bandwidth consumption. In fact, the appearance of jamming attacks in OTA-FL systems can severely disrupt the convergence. This paper studies the problem of jamming attacks and its countermeasures in over-the-air federated learning (OTA-FL). To this end, we propose the coordinated dropout strategy (CoDrop), which enables AIoT devices to collaboratively drop out (i.e., to refrain from transmitting) part of their gradients so that the jamming signals aggregated in received signals can be accurately measured and mitigated. Our simulation results reveal that CoDrop is effective in alleviating the negative impacts of jamming signals with significantly low dropout rates, and it is shown to converge well as compared to existing solutions under various parameter settings.
dc.format.extent 115 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) 2025 IEEE Global Communications Conference (GLOBECOM) Proceedings, IEEE Communications Society, pp.3958-3963
dc.subject (關鍵詞) Federated learning; over-the-air computation; jamming attacks; dropout; Artificial Intelligence of Things
dc.title (題名) Mitigating Jamming Attacks in Over-the-Air Federated Learning via Coordinated Dropout
dc.type (資料類型) conference
dc.identifier.doi (DOI) 10.1109/GLOBECOM59602.2025.11432204
dc.doi.uri (DOI) https://doi.org/10.1109/GLOBECOM59602.2025.11432204