Design and Development of A Novel CNN-BiLSTM Hybrid Deep Learning Model for Cyber Attacks Detection in an IoHT Environment

IoHT, a subset of IoT, creates a network where medical devices and sensors communicate to exchange essential health-related data. An in-depth review of existing literature underscores a significant rise in malware attacks, which parallels the extensive incorporation of Internet of Health Things (IoHT) devices. The impact of Malware attacks in the IoHT environment extends beyond just technological and financial aspects to include patient safety, privacy, and trust in healthcare systems. Vulnerabilities in IoHT systems or insufficient security measures can result in unauthorized access to patient health information and sensitive medical data. The novel CNN-BiLSTM hybridized deep learning model showcased in this research is intended to efficiently detect and classify cyberattacks in the context of the Internet of Health by utilizing the most recent ECU-IoHT dataset. Throughout all experimental trials, the proposed method consistently outperformed several established approaches in the realm of IoHT malware detection, achieving an impressive accuracy level of 99.51%.