An improved implicit authentication framework using the event-driven and context-aware approaches

In the digital age, safeguarding personal data on smartphones and wearable devices is more critical than ever. Implicit authentication has become a hot research direction in the field of security. Aiming to offer a seamless and secure user experience, this study presents an improved implicit authentication framework that enhances mobile security. By integrating metabolic equivalent of task (MET) data into context awareness module that detects user’s activity intensity, the system smartly adapts the dynamic and static authentication models, ensuring accuracy without compromising user convenience. The dynamic and static authentication models are developed based on the Random Forest algorithm. The approach also operates on an event-triggered mechanism, activating the authentication process only during specified activities such as unusual phone calls or Wi-Fi changes. This study found that the proposed model not only helps to improve the accuracy of implicit authentication, but also significantly reduces the computational and power burden on devices, enhancing the practicality of implicit identity authentication.