Nonintrusive Smartphone User Verification Using Anonymized Multimodal Data

Abstract

Smartphone user verification is important as personal daily activities are increasingly conducted on the phone and sensitive information is constantly logged. The commonly adopted user verification methods are typically active, i.e., they require a user's cooperative input of a security token to gain access permission. Though popular, these methods impose heavy burden to smartphone users to memorize, maintain, and input the token at a high frequency. To alleviate this imposition onto the users and to provide additional security, we propose a new nonintrusive and continuous mobile user verification framework that can reduce the frequency required for a user to input his/her security token. Using tailored Hidden Markov Models and sequential likelihood ratio test, our verification is built on low-cost, readily available, anonymized, and multimodal smartphone data without additional effort of data collection and risk of privacy leakage. With extensive evaluation, we achieve a high rate of about 94 percent for detecting illegitimate smartphone uses and a rate of 74 percent for confirming legitimate uses. In a practical setting, this can translate into 74 percent of frequency reduction of inputting a security token using an active authentication method with only about 6 percent risk of miss detection of a random intruder, which is highly desirable.