The Partially Observable Hidden Markov Model and its Application to Keystroke Dynamics
This work addresses biometric security challenges by improving keystroke-based user authentication, though it is incremental as it extends existing HMM methods.
The authors tackled the problem of modeling keystroke dynamics for biometric identification and verification by proposing a partially observable hidden Markov model that incorporates event types like key names. The model consistently outperformed other anomaly detectors, including standard HMMs, across five public datasets.
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.