Privacy-Preserving Intrusion Detection in Software-defined VANET using Federated Learning with BERT
Shakil Ibne Ahsan, Phil Legg, S M Iftekharul Alam
TL;DR
The paper addresses privacy-preserving intrusion detection in software-defined VANETs by proposing FL-BERT, a framework that combines Federated Learning with the BERT model for sequence classification on the VeReMi dataset. It benchmarks FL-BERT against conventional machine learning models (RF, SVM, LR, KNN) trained on TF-IDF features, observing that FL-BERT achieves about 84% accuracy and outperforms the baselines in overall attack detection. Privacy is preserved by keeping raw data locally on clients and aggregating model updates at a central server through a mixture-based global model, with periodic re-initialization to mitigate overfitting and leakage risks. The study also discusses per-attack-type performance variations and potential privacy vulnerabilities such as model inversion, suggesting enhancements like differential privacy for future work to strengthen security in VANET environments.
Abstract
The absence of robust security protocols renders the VANET (Vehicle ad-hoc Networks) network open to cyber threats by compromising passengers and road safety. Intrusion Detection Systems (IDS) are widely employed to detect network security threats. With vehicles' high mobility on the road and diverse environments, VANETs devise ever-changing network topologies, lack privacy and security, and have limited bandwidth efficiency. The absence of privacy precautions, End-to-End Encryption methods, and Local Data Processing systems in VANET also present many privacy and security difficulties. So, assessing whether a novel real-time processing IDS approach can be utilized for this emerging technology is crucial. The present study introduces a novel approach for intrusion detection using Federated Learning (FL) capabilities in conjunction with the BERT model for sequence classification (FL-BERT). The significance of data privacy is duly recognized. According to FL methodology, each client has its own local model and dataset. They train their models locally and then send the model's weights to the server. After aggregation, the server aggregates the weights from all clients to update a global model. After aggregation, the global model's weights are shared with the clients. This practice guarantees the secure storage of sensitive raw data on individual clients' devices, effectively protecting privacy. After conducting the federated learning procedure, we assessed our models' performance using a separate test dataset. The FL-BERT technique has yielded promising results, opening avenues for further investigation in this particular area of research. We reached the result of our approaches by comparing existing research works and found that FL-BERT is more effective for privacy and security concerns. Our results suggest that FL-BERT is a promising technique for enhancing attack detection.