Continuous authentication of smartphone users based on activity pattern recognition using passive mobile sensing

Muhammad Ehatisham-ul-Haq, Muhammad Awais Azam, Usman Naeem, Yasar Amin, Jonathan Loo
2018 Journal of Network and Computer Applications  
Smartphones are inescapable devices, which are becoming more and more intelligent and 10 context-aware with emerging sensing, networking and computing capabilities. They offer a captivating 11 platform to the users for performing a wide variety of tasks including socializing, communication, sending or 12 receiving emails, storing and accessing personal data etc. at anytime and anywhere. Nowadays, loads of people 13 tend to store different types of private and sensitive data in their smartphones
more » ... including bank account details, 14 personal identifiers, accounts credentials, and credit card details. A lot of people keep their personal e-accounts 15 logged in all the time in their mobile devices. Hence these mobile devices are prone to different security and 16 privacy threats and attacks from the attackers. Commonly used approaches for securing mobile devices such as 17 passcode, PINs, pattern lock, face recognition, and fingerprint scan are vulnerable and exposed to several 18 attacks including smudge attacks, side-channel attacks, and shoulder-surfing attacks. To address these 19 challenges, a novel continuous authentication scheme is presented in this study, which recognizes smartphone 20 users on the basis of their physical activity patterns using accelerometer, gyroscope, and magnetometer sensors 21 of smartphone. A series of experiments are performed for user recognition using different machine learning 22 classifiers, where six different activities are analyzed for the multiple locations of smartphone on the user's 23 body. SVM classifier achieved the best results for user recognition with an overall average accuracy of 97.95%. 24 A comprehensive analysis of the user recognition results validates the efficiency of the proposed scheme. 25
doi:10.1016/j.jnca.2018.02.020 fatcat:4tu22aitbzaqxjbmpnsbkakhde