Journal Article

Identifying significant features in adversarial attack detection framework using federated learning empowered medical IoT network security

Nooh, Sameer, Sharaf, Sanaa A.

2025

Overview

The expansion of the Internet of Medical Things (IoHT) presents significant advantages for healthcare over improved data-driven insights and connectivity and offers critical cybersecurity challenges. Attacks are a serious risk for neural network security; recent defence mechanisms remain restricted concerning their applicability to real-world environments. The influence of adversarial attacks is essential, as they can challenge the security and reliability of Artificial Intelligence (AI) methods in crucial applications. Dealing with these vulnerabilities is vital to develop strong and reliable NNs. Therefore, the study of adversarial defence mechanisms and attack detection became an important area in the domain of AI. Machine learning (ML) and specific deep learning (DL) models have recently influenced excellent performance on challenging perceptual tasks like adversarial attack detection. Meanwhile, the federated learning (FL) method is susceptible to attacks by malicious clients. FL can complete a considerable training task effectively by attracting participants for training a DL method cooperatively, and the user privacy should be completely protected for the users only upload model parameters to the centralized server. This study presents an Adversarial Attack Detection Framework Using Federated Learning Empowered IoT Medical (AADF-FLEIoTM) model. The main intention of the AADF-FLEIoTM model is to develop adversarial attack detection using FL and an advanced hybrid model. The data normalization stage initially uses min-max normalization to scale and transform data into a consistent range. The proposed AADF-FLEIoTM employs the marine predator algorithm (MPA) model to identify and retain the most relevant features for the feature selection process. Besides, the integration of convolutional neural networks, bidirectional long short-term memory, and self-attention (SA-CNN-BiLSTM) technique is utilized for the detection and classification process. Finally, the Red-Tail Hawk (RTH)-optimizer algorithm alters the hyperparameter values of the SA-CNN-BiLSTM technique optimally and results in more excellent classification performance. The AADF-FLEIoTM approach is examined on the IoT healthcare security dataset. The performance validation of the AADF-FLEIoTM approach illustrated a superior accuracy value of 98.24% over existing models.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 639/705/1042 / 639/705/258 / Adversarial attack detection / Algorithms / Artificial Intelligence / Blockchain / Classification / Computer Security / Confidentiality / Cybersecurity / Datasets / Deep Learning / Defense mechanisms / Efficiency / Feature selection / Federated Learning / Ground stations / Health care / Humanities and Social Sciences / Humans / Internet of Things / Long short-term memory / Machine Learning / Medical IoT network / Methods / multidisciplinary / Neural networks / Neural Networks, Computer / Optimization techniques / Privacy / Red-Tail hawk optimizer / Science / Science (multidisciplinary)