Biometric Recognition Based on Free-Text Keystroke Dynamics

Abstract

Accurate recognition of free text keystroke dynamics is challenging due to the unstructured and sparse nature of the data and its underlying variability. As a result, most of the approaches published in the literature on free text recognition, except for one recent one, have reported extremely high error rates. In this paper, we present a new approach for the free text analysis of keystrokes that combines monograph and digraph analysis, and uses a neural network to predict missing digraphs based on the relation between the monitored keystrokes. Our proposed approach achieves an accuracy level comparable to the best results obtained through related techniques in the literature, while achieving a far lower processing time. Experimental evaluation involving 53 users in a heterogeneous environment yields a false acceptance ratio (FAR) of 0.0152% and a false rejection ratio (FRR) of 4.82%, at an equal error rate (EER) of 2.46%. Our follow-up experiment, in a homogeneous environment with 17 users, yields FAR=0% and FRR=5.01%, at EER=2.13%.

Utilizing overt and latent linguistic structure to improve keystroke-based authentication

“…Finally, 88% of subjects reported being right-hand dominant, while 9% reported being left-handed. 1 The mean typing rate of the users was 168.9 intraword keystrokes per minute [2] with a standard deviation of 50.04.…”

User Authentication Based on Keystroke Dynamics of Free Text and One-Class Classifiers

“…생체 인증에서는 사람마다 고유한 패턴을 가지는 DNA, 귀(귓바퀴의 연골 조직 구조), 얼굴, 안면 또는 손목 정맥 열상, 지문, 손과 손가락 모양, 홍채, 체취, 손금, 망막 등의 소 유적 생체 정보(possessive biometrics)나 음성, 걸음걸이, 서명, 키스트로크 다이나믹스 등의 행위적 생체 정보(behavioral biometrics)가 사용될 수 있다. 그 중 DNA, 지문, 홍채, 손금, 망막 은 상대적으로 높은 인식 정확도를 가지는 것으로 알려져 있 으나, 이러한 소유적 생체 정보를 사용자 인증에 활용하기 위 해서는 지문 인식 센서, 적외선 카메라, 홍채 인식 센서와 같은 인식 장치(하드웨어)의 추가적인 설치가 필수적이라는 단점이 존재한다 (Jain et al, 2004;Samura and Nishimura, 2012 (Roth et al, 2013;Ahmed and Traore, 2014;Bours and Soumik, 2015). 키스트로크 다이나믹스 기반 사용자 인증에서는 입력된 문 자열의 정보 및 이 문자열을 입력할 때 소요되는 시간 정보를 이 용하여 사용자의 고유한 타이핑 패턴을 학습하게 된다 (Alsultan and Warwick, 2013 (Davoudi and Kabir, 2009;Bours and Soumik, 2015;Kang and Cho, 2015).…”

Authorship verification using deep belief network systems

“…The strength of a CA system depends on the adequacy/strength of the underlying authentication modalities. In the literature, CA using biometric modalities have been extensively studied, but CA using stylometry is yet to be widely explored . Stylometric analysis involves establishing a document's authorship on the basis of sample writing styles.…”