The Partially Observable Hidden Markov Model and its Application to Keystroke Dynamics

TL;DR

This paper introduces the partially observable hidden Markov model (POHMM), extending HMMs to incorporate external metadata, and demonstrates its effectiveness in keystroke dynamics biometric applications using multiple datasets.

Contribution

The paper proposes the POHMM, integrating independent Markov chains for external metadata, and shows its superior performance over standard HMMs in keystroke biometric tasks.

Findings

POHMM outperforms standard HMM in biometric identification.

POHMM is preferred in goodness of fit tests.

Model effectively captures external metadata influence.

Abstract

The partially observable hidden Markov model is an extension of the hidden Markov Model in which the hidden state is conditioned on an independent Markov chain. This structure is motivated by the presence of discrete metadata, such as an event type, that may partially reveal the hidden state but itself emanates from a separate process. Such a scenario is encountered in keystroke dynamics whereby a user's typing behavior is dependent on the text that is typed. Under the assumption that the user can be in either an active or passive state of typing, the keyboard key names are event types that partially reveal the hidden state due to the presence of relatively longer time intervals between words and sentences than between letters of a word. Using five public datasets, the proposed model is shown to consistently outperform other anomaly detectors, including the standard HMM, in biometric identification and verification tasks and is generally preferred over the HMM in a Monte Carlo goodness of fit test.