Invention Grant
US08136154B2 Hidden markov model (“HMM”)-based user authentication using keystroke dynamics
有权
基于隐马尔可夫模型（“HMM”）的用户认证使用按键动力学
- Patent Title: Hidden markov model (“HMM”)-based user authentication using keystroke dynamics
- Patent Title (中): 基于隐马尔可夫模型（“HMM”）的用户认证使用按键动力学
-
Application No.: US12116142Application Date: 2008-05-06
-
Publication No.: US08136154B2Publication Date: 2012-03-13
- Inventor: Vir V. Phoha , Shashi Phoha , Asok Ray , Shrijit Sudhakar Joshi , Sampath Kumar Vuyyuru
- Applicant: Vir V. Phoha , Shashi Phoha , Asok Ray , Shrijit Sudhakar Joshi , Sampath Kumar Vuyyuru
- Applicant Address: US PA University Park US LA Ruston
- Assignee: The Penn State Foundation,Louisiana Tech Unversity Research Foundation
- Current Assignee: The Penn State Foundation,Louisiana Tech Unversity Research Foundation
- Current Assignee Address: US PA University Park US LA Ruston
- Agency: Blakely Sokoloff Taylor & Zafman LLP
- Main IPC: G06F7/04
- IPC: G06F7/04
Abstract:
Hidden Markov Models (“HMMs”) are used to analyze keystroke dynamics measurements collected as a user types a predetermined string on a keyboard. A user enrolls by typing the predetermined string several times; the enrollment samples are used to train a HMM to identify the user. A candidate who claims to be the user provides a typing sample, and the HMM produces a probability to estimate the likelihood that the candidate is the user he claims to be. A computationally-efficient method for preparing HMMs to analyze certain types of processes is also described.
Public/Granted literature
- US20090328200A1 Hidden Markov Model ("HMM")-Based User Authentication Using Keystroke Dynamics Public/Granted day:2009-12-31
Information query
