Enhancing Federated Learning Security: Combating Clients’ Data Poisoning with Classifier Ensembles DOI
Arunava Roy,

Dipankar Dasgupta

Опубликована: Окт. 28, 2024

Язык: Английский

Over-the-air federated learning: Status quo, open challenges, and future directions DOI Creative Commons
Bingnan Xiao, Xichen Yu, Wei Ni

и другие.

Fundamental Research, Год журнала: 2024, Номер unknown

Опубликована: Фев. 1, 2024

The development of applications based on artificial intelligence and implemented over wireless networks is increasingly rapidly expected to grow dramatically in the future. resulting demand for aggregation large amounts data has caused serious communication bottlenecks particularly at network edge. Over-the-air federated learning (OTA-FL), leveraging superposition feature multi-access channels (MACs), enables users edge share spectrum resources achieves efficient low-latency global model aggregation. This paper provides a holistic review progress OTA-FL points potential future research directions. Specifically, we classify from perspective system settings, including single-antenna OTA-FL, multi-antenna with aid emerging reconfigurable intelligent surface (RIS) technology, contributions existing works these areas are summarized. Moreover, discuss trust, security privacy aspects highlight concerns arising privacy. Finally, challenges directions discussed promote terms improving performance, reliability, trustworthiness. Specifical be addressed include distortion under channel fading, ineffective OTA local models trained substantially unbalanced data, limited accessibility verifiability individual models.

Язык: Английский

Процитировано

9
Temporal Convolutional Network Approach to Secure Open Charge Point Protocol (OCPP) in Electric Vehicle Charging DOI Creative Commons

Ikram Benfarhat,

Vik Tor Goh, Siow Chun Lim

и другие.

IEEE Access, Год журнала: 2025, Номер 13, С. 15272 - 15289

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1
A hybrid and efficient Federated Learning for privacy preservation in IoT devices DOI
Shaohua Cao,

Shangru Liu,

Yansheng Yang

и другие.

Ad Hoc Networks, Год журнала: 2025, Номер unknown, С. 103761 - 103761

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1
AWE-DPFL: Adaptive weighting and dynamic privacy budget federated learning for heterogeneous data in IoT DOI

Guiping Zheng,

Bei Gong, Chong Guo

и другие.

Computers & Electrical Engineering, Год журнала: 2025, Номер 123, С. 110070 - 110070

Опубликована: Янв. 22, 2025

Язык: Английский

Процитировано

1
Defending Against Poisoning Attacks in Federated Learning With Blockchain DOI Creative Commons
Nanqing Dong, Zhipeng Wang, Jiahao Sun

и другие.

IEEE Transactions on Artificial Intelligence, Год журнала: 2024, Номер 5(7), С. 3743 - 3756

Опубликована: Март 18, 2024

In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owners, or clients, to collaboratively train machine models without compromising privacy. However, most existing FL approaches rely on centralized server for global model aggregation, leading single point failure. This makes system vulnerable malicious attacks when dealing with dishonest clients. this work, we address problem by proposing secure and reliable based blockchain distributed ledger technology. Our incorporates peer-to-peer voting mechanism reward-and-slash mechanism, which are powered on-chain smart contracts, detect deter behaviors. Both theoretical empirical analyses presented demonstrate effectiveness proposed approach, showing our framework is robust against client-side

Язык: Английский

Процитировано

5
M2FD: Mobile malware federated detection under concept drift DOI Creative Commons
Andrea Augello, Alessandra De Paola, Giuseppe Lo Re

и другие.

Computers & Security, Год журнала: 2025, Номер unknown, С. 104361 - 104361

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
Mitigating Over-Unlearning in Machine Unlearning with Synthetic Data Augmentation DOI

B. L. Wang,

Youyang Qu, Longxiang Gao

и другие.

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 300 - 314

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
A Review and Experimental Evaluation on Split Learning DOI Creative Commons
Zhanyi Hu, Tianchen Zhou, Bingzhe Wu

и другие.

Future Internet, Год журнала: 2025, Номер 17(2), С. 87 - 87

Опубликована: Фев. 13, 2025

Training deep learning models collaboratively on decentralized edge devices has attracted significant attention recently. The two most prominent schemes for this problem are Federated Learning (FL) and Split (SL). Although there have been several surveys experimental evaluations FL in the literature, SL paradigms not yet systematically reviewed evaluated. Due to diversity of terms label sharing, model aggregation, cut layer selection, etc., lack a systematic survey makes it difficult fairly conveniently compare performance different paradigms. To address above issue, paper, we first provide comprehensive review existing Then, implement typical perform extensive experiments their scenarios four widely used datasets. results engineering advice research insights We hope that our work can facilitate future by establishing fair accessible benchmark evaluation.

Язык: Английский

Процитировано

0
Modal-Centric Insights Into Multimodal Federated Learning for Smart Healthcare: A Survey DOI
Di Wang, Wenjian Liu, Longxiang Gao

и другие.

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 145 - 160

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Securing federated learning: a defense strategy against targeted data poisoning attack DOI Creative Commons
Ansam Khraisat, Ammar Alazab, Moutaz Alazab

и другие.

Discover Internet of Things, Год журнала: 2025, Номер 5(1)

Опубликована: Фев. 24, 2025

Язык: Английский

Процитировано

0