Split Learning-Enabled Framework for Secure and Light-weight Internet of Medical Things Systems
This addresses security risks in medical IoT systems by offering a more efficient and private alternative to existing methods, though it is incremental as it builds on split learning for a specific domain.
The paper tackles malware detection in resource-constrained Internet of Medical Things devices by proposing a split learning framework that divides neural network training between clients and an edge server, achieving improvements such as +6.35% accuracy and 33.83% less resource consumption compared to federated learning methods.
The rapid growth of Internet of Medical Things (IoMT) devices has resulted in significant security risks, particularly the risk of malware attacks on resource-constrained devices. Conventional deep learning methods are impractical due to resource limitations, while Federated Learning (FL) suffers from high communication overhead and vulnerability to non-IID (heterogeneous) data. In this paper, we propose a split learning (SL) based framework for IoT malware detection through image-based classification. By dividing the neural network training between the clients and an edge server, the framework reduces computational burden on resource-constrained clients while ensuring data privacy. We formulate a joint optimization problem that balances computation cost and communication efficiency by using a game-theoretic approach for attaining better training performance. Experimental evaluations show that the proposed framework outperforms popular FL methods in terms of accuracy (+6.35%), F1-score (+5.03%), high convergence speed (+14.96%), and less resource consumption (33.83%). These results establish the potential of SL as a scalable and secure paradigm for next-generation IoT security.