.png){kind=icon}
Return
A Distributed Attack-Resistant Trust Model for Automatic Modulation Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/LCOMM.2022.3194020.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently, the performance of automatic modulation recognition (AMC) has been dramatically improved with the assistance of federated learning (FL). However, FL-based AMC still faces the issue of secure sharing of local model parameters, resulting in poor anti-attack capacity. Motivated by this, a Blockchain-federated learning (BFL) framework is proposed for AMC in this letter, where the AMC model is cooperatively trained by the sharing of local model parameters with Blockchain. In addition, a parameter validity evaluation method is designed therein for the aggregation process, which greatly weakens the influence of malicious nodes. On the basis of enriching training samples, the anti-attack ability of FL-based AMC schemes is significantly improved for proposed BFL framework. Simulation results show that the recognition accuracy of the proposed framework is increased by more than 10% when malicious nodes exist, on the premise of acceptable recognition accuracy.
Keywords:
Computational modeling
Data models
Consensus protocol
Training
Indexes
Simulation
Signal to noise ratio
Federated learning
automatic modulation classification
blockchain
validity evaluation
Journal
IF:
4.4
Papers:
1.3W
Citations:
2.2W
Organization
Cited Papers
ShareSaveRobust Automatic Modulation Recognition Through Joint Contribution of Hand-Crafted and Contextual Features.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSaveShareSaveShareSaveData-Driven Abnormity Assessment for Low-Voltage Power Consumption and Supplies Based on CRITIC and Improved Radar Chart AlgorithmsIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAIShareSave
View more