PATH: Person Authentication using Trace Histories

TL;DR

This paper introduces MSHMM, a novel Markov model-based approach for active user authentication on mobile devices using location trace histories, outperforming existing methods in accuracy.

Contribution

The paper proposes the Marginally Smoothed HMM (MSHMM), a new method that improves user verification by effectively handling unforeseen observations in location trace data.

Findings

MSHMM outperforms sequence matching, Markov chain, and basic HMM methods in EER.

Experimental results on UMD and GeoLife datasets validate the effectiveness of MSHMM.

Parameter analysis shows robustness of the proposed approach.

Abstract

In this paper, a solution to the problem of Active Authentication using trace histories is addressed. Specifically, the task is to perform user verification on mobile devices using historical location traces of the user as a function of time. Considering the movement of a human as a Markovian motion, a modified Hidden Markov Model (HMM)-based solution is proposed. The proposed method, namely the Marginally Smoothed HMM (MSHMM), utilizes the marginal probabilities of location and timing information of the observations to smooth-out the emission probabilities while training. Hence, it can efficiently handle unforeseen observations during the test phase. The verification performance of this method is compared to a sequence matching (SM) method , a Markov Chain-based method (MC) and an HMM with basic Laplace Smoothing (HMM-lap). Experimental results using the location information of the UMD Active Authentication Dataset-02 (UMDAA02) and the GeoLife dataset are presented. The proposed MSHMM method outperforms the compared methods in terms of equal error rate (EER). Additionally, the effects of different parameters on the proposed method are discussed.