To date, many previous studies have been proposed for driver authentication; however, these solutions have many shortcomings and are still far from practical for real-world applications. In this paper, we tackle the shortcomings of the existing solutions and reach toward proposing a lightweight and practical authentication system, dubbed DriveMe, for identifying drivers on cars. Our novelty aspects are ① Lightweight scheme that depends only on a single sensor data (i.e., pressure readings) attached to the driver’s seat and belt. ② Practical evaluation in which one-class authentication models are trained from only the owner users and tested using data collected from both owners and attackers. ③ Rapid Authentication to quickly identify drivers’ identities using a few pressure samples collected within short durations (1, 2, 3, 5, or 10 s). ④ Realistic experiments where the sensory data is collected from real experiments rather than computer simulation tools. We conducted real experiments and collected about 13,200 samples and 22,800 samples of belt-only and seat-only datasets from all 12 users under different settings. To evaluate system effectiveness, we implemented extensive evaluation scenarios using four one-class detectors One-Class Support Vector Machine (OCSVM), Local Outlier Factor (LOF), Isolation Forest (IF), and Elliptic Envelope (EE), three dataset types (belt-only, seat-only, and fusion), and four different dataset sizes. Our average experimental results show that the system can authenticate the driver with an F1 score of 93.1% for seat-based data using OCSVM classifier, an F1 score of 98.53% for fusion-based data using LOF classifier, an F1 score of 91.65% for fusion-based data using IF classifier, and an F1 score of 95.79% for fusion-based data using EE classifier.

Nowadays, the use of Avatars that are unique digital depictions has increased by users to access Metaverse—a virtual reality environment—through multiple devices and for various purposes. Therefore, the Avatar and Metaverse are being developed with a new theory, application, and design, necessitating the association of more personal data and devices of targeted users every day. This Avatar and Metaverse technology explosion raises privacy and security concerns, leading to cyber attacks. MV-Honeypot, or Metaverse-Honeypot, as a commercial off-the-shelf solution that can counter these cyber attack-causing vulnerabilities, should be developed. To fill this gap, we study user’s engagements with Avatars in Metaverse, analyze possible security vulnerabilities, and create a model named Simplified Avatar Relationship Association with Non-linear Gradient (SARANG) that draws the full diagram of infrastructure components and data flow through accessing Metaverse in this paper. We also determine the most significant threat for each component’s cyberattacks that will affect user data and Avatars. As a result, the commercial off-the-shelf (COTS) of the MV-Honeypot must be established.