Combining Keystroke Dynamics and Face Recognition for User Verification

Abstract

Abstract²The massive explosion and ubiquity of computing devices and the outreach of the web have been the most defining events of the century so far. As more and more people gain access to the internet, traditional know-something and have-something authentication methods such as PINs and passwords are proving to be insufficient for prohibiting unauthorized access to increasingly personal data on the web. Therefore, the need of the hour is a user-verification system that is not only more reliable and secure, but also unobtrusive and minimalistic. Keystroke Dynamics is a novel Biometric Technique; it is not only unobtrusive, but also transparent and inexpensive. The fusion of keystroke dynamics and Face Recognition engenders the most desirable characteristics of a verification system. Our implementation uses Hidden Markov Models (HMM) for modeling the Keystroke Dynamics, with the help of two widely used Feature Vectors: Keypress Latency and Keypress Duration. On the other hand, Face Recognition makes use of the traditional Eigenfaces approach. The results show that the system has a high precision, with a False Acceptance Rate of 5.4% and a False Rejection Rate of 9.2%. Moreover, it is also future-proof, as the hardware requirements, i.e. camera and keyboard (physical or on-screen), have become an indispensable part of modern computing.

A Systematic Survey on Examinees Identity Authentication in Online Distant Exams

“…For example, Fenu, Marras and Boratto building a template containing features of the following five modalities, face images, voice data, touch data, mouse data, and keystroke dynamics [82]. The student's face will be captured and stored in addition to the student's dynamic keystrokes [14,83,84]. Alternatively, Shen, et.al.…”

A Secure and Scalable Behavioral Dynamics Authentication Model

“…In this regard, biometric features unique to individuals, ranging from physiological characteristics (e.g., fingerprints and iris, hand, and face patterns) to behavioral characteristics (e.g., KD, www.ijacsa.thesai.org mouse movements, gait, and handwriting), have served to identify users [3]. Many such biometric approaches tend either to be expensive or to place heavy demands on computer hardware, making them inappropriate for most users [35].…”

“…Jadhav Kulkami, Shelar, Shinde, and Dharwadkar [3] proposed an ML-based authentication model that uses the static approach of keystroke dynamics to recognize and authenticate users accessing the system based on their unique keystroke profiles with respect to the flight, dwell, press, press-to-press, and release-to-release time and achieved an FAR and an FRR of 1% and 4%, respectively. Gupta, Khanna, Jagetia, Sharma, Alekh, and Chouldhary [35] proposed a high-efficiency authentication system combining two methods to make keystroke biometrics less susceptible to forgery and more usable and reported that the system efficiently implemented secure authentication with the advantage of ease of implementation since all that is required is the installation of software on any workstation. Yang et al [55] focused on the text entered by the user and proposed contents and keystroke dual attention networks (ML) with pre-trained models for continuous authentication to address user-inputted -text‖ during keystrokes as an important asset beyond traditional KD characteristics, and their model achieved state-of-the-art performance on two datasets.…”