Enhancing Data Privacy of IoT Healthcare with Keylogger Attack Mitigation

The healthcare industry has been revolutionized by the Internet of Things (IoT), which has made it possible to develop various applications to monitor patients' health conditions and provide customized care. One of the ways in which IoT is being used in healthcare is through remote patient monitoring. This involves collecting real-time data from IoT-enabled devices such as blood pressure monitors, thermometers, and heart rate monitors, which can help healthcare professionals detect and respond to changes in a patient's health condition before they become critical. Despite the numerous benefits of IoT healthcare applications, there are critical security concerns that need to be addressed. One such concern is data privacy, as IoT devices collect a significant amount of sensitive patient information that needs to be protected from unauthorized access, hacking, and breaches. Another issue is the vulnerability of IoT devices to malware and hacking attacks due to inadequate security protections and outdated software. IoT devices can be utilized by cyber attackers to remotely get the patent’s data by causing keylogger attacks. The harm caused by keylogger attacks is significant, as they compromise private information such as patients’ private details, leading to identity theft and other crimes. These attacks can also cause operational problems such as degraded response time of IoT healthcare, system crashes, and corrupted files. Keyloggers can be difficult to detect as they run covertly in the background. In this paper, a methodology is proposed for early detection of keylogger attacks in IoT healthcare to preserve the patient’s identity from cyber attackers using the machine learning-based approach. The proposed framework is experimented on IoT healthcare dataset for comparing the performance of LightGBM, CNN, and ANN machine learning models.