Continuous User Authentication Based on Keystroke Dynamics through Neural Network Committee Machines

2013 ◽  
pp. 410-429
Author(s):  
Sérgio Roberto de Lima e Silva Filho ◽  
Mauro Roisenberg
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
User Authentication ◽  
Keystroke Dynamics ◽  
Continuous Authentication ◽  
Biometric Characteristic ◽  
Continuous User ◽  
Computer Keyboard

This chapter proposes an authentication methodology that is both inexpensive and non-intrusive and authenticates users continuously while using a computer keyboard. This proposed methodology uses neural network committee machines. The committee consists of several independent neural networks trained to recognize a behavioral biometric characteristic: user’s typing pattern. Continuous authentication prevents potential attacks when users leave their desks without logging out or locking their computer session. Some experiments were conducted to evaluate and to calibrate the authentication committee. Best results show that a 0% FAR and a 0.15% FRR can be achieved when different thresholds are used in the system for each user. In this proposed methodology, capture system does not need to concern about typing errors in the text. Another feature of this methodology is that new users can be easily added to the system, with no need to re-train all neural networks involved.

Continuous User Authentication Based on Keystroke Dynamics through Neural Network Committee Machines

2011 ◽  
pp. 232-252
Author(s):  
Sérgio Roberto de Lima e Silva Filho ◽  
Mauro Roisenberg
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
User Authentication ◽  
Keystroke Dynamics ◽  
Continuous Authentication ◽  
Biometric Characteristic ◽  
Continuous User ◽  
Computer Keyboard

This chapter proposes an authentication methodology that is both inexpensive and non-intrusive and authenticates users continuously while using a computer keyboard. This proposed methodology uses neural network committee machines. The committee consists of several independent neural networks trained to recognize a behavioral biometric characteristic: user’s typing pattern. Continuous authentication prevents potential attacks when users leave their desks without logging out or locking their computer session. Some experiments were conducted to evaluate and to calibrate the authentication committee. Best results show that a 0% FAR and a 0.15% FRR can be achieved when different thresholds are used in the system for each user. In this proposed methodology, capture system does not need to concern about typing errors in the text. Another feature of this methodology is that new users can be easily added to the system, with no need to re-train all neural networks involved.

A Lightweight Privacy-Aware Continuous Authentication Protocol-PACA

2021 ◽  
Vol 24 (4) ◽  
pp. 1-28
Author(s):  
Abbas Acar ◽  
Shoukat Ali ◽  
Koray Karabina ◽  
Cengiz Kaygusuz ◽  
Hidayet Aksu ◽  
...  
Keyword(s):  
Template Matching ◽  
User Authentication ◽  
Third Party ◽  
Biometric Data ◽  
Concrete System ◽  
Current State ◽  
Continuous Authentication ◽  
User Data ◽  
Continuous User ◽  
Privacy Issues

As many vulnerabilities of one-time authentication systems have already been uncovered, there is a growing need and trend to adopt continuous authentication systems. Biometrics provides an excellent means for periodic verification of the authenticated users without breaking the continuity of a session. Nevertheless, as attacks to computing systems increase, biometric systems demand more user information in their operations, yielding privacy issues for users in biometric-based continuous authentication systems. However, the current state-of-the-art privacy technologies are not viable or costly for the continuous authentication systems, which require periodic real-time verification. In this article, we introduce a novel, lightweight, <underline>p</underline>rivacy-<underline>a</underline>ware, and secure <underline>c</underline>ontinuous <underline>a</underline>uthentication protocol called PACA. PACA is initiated through a password-based key exchange (PAKE) mechanism, and it continuously authenticates users based on their biometrics in a privacy-aware manner. Then, we design an actual continuous user authentication system under the proposed protocol. In this concrete system, we utilize a privacy-aware template matching technique and a wearable-assisted keystroke dynamics-based continuous authentication method. This provides privacy guarantees without relying on any trusted third party while allowing the comparison of noisy user inputs (due to biometric data) and yielding an efficient and lightweight protocol. Finally, we implement our system on an Apple smartwatch and perform experiments with real user data to evaluate the accuracy and resource consumption of our concrete system.

scholarly journals Deep Residual Networks for User Authentication via Hand-Object Manipulations

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2981
Author(s):  
Kanghae Choi ◽  
Hokyoung Ryu ◽  
Jieun Kim
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
User Authentication ◽  
Ecological Validity ◽  
Age Groups ◽  
Rejection Rate ◽  
Object Manipulation ◽  
Measurement Unit ◽  
Validity Data ◽  
Continuous User

With the ubiquity of wearable devices, various behavioural biometrics have been exploited for continuous user authentication during daily activities. However, biometric authentication using complex hand behaviours have not been sufficiently investigated. This paper presents an implicit and continuous user authentication model based on hand-object manipulation behaviour, using a finger-and hand-mounted inertial measurement unit (IMU)-based system and state-of-the-art deep learning models. We employed three convolutional neural network (CNN)-based deep residual networks (ResNets) with multiple depths (i.e., 50, 101, and 152 layers) and two recurrent neural network (RNN)-based long short-term memory (LSTMs): simple and bidirectional. To increase ecological validity, data collection of hand-object manipulation behaviours was based on three different age groups and simple and complex daily object manipulation scenarios. As a result, both the ResNets and LSTMs models acceptably identified users’ hand behaviour patterns, with the best average accuracy of 96.31% and F1-score of 88.08%. Specifically, in the simple hand behaviour authentication scenarios, more layers in residual networks tended to show better performance without showing conventional degradation problems (the ResNet-152 > ResNet-101 > ResNet-50). In a complex hand behaviour scenario, the ResNet models outperformed user authentication compared to the LSTMs. The 152-layered ResNet and bidirectional LSTM showed an average false rejection rate of 8.34% and 16.67% and an equal error rate of 1.62% and 9.95%, respectively.

scholarly journals On keystrokes as Continuous User Biometric Authentication

2019 ◽  
Vol 8 (6) ◽  
pp. 4149-4153
Keyword(s):  
User Authentication ◽  
Support Vector ◽  
Free Text ◽  
Biometric Authentication ◽  
Text Input ◽  
Continuous Authentication ◽  
Online Examination ◽  
Continuous User ◽  
Authentication System ◽  
Identification Phase

Authentication of a user through an ID and password is generally done at the start of a session. But the continuous authentication system observe the genuineness of the user throughout the entire session, and not at login only. In this paper, we propose the usage of keystroke dynamics as biometric trait for continuous user authentication in desktop platform. Biometric Authentication involves mainly three phases named as enrollment phase, verification phase and identification phase. The identification phase marks the accessed user as an authenticated only if the input pattern matches with the profile pattern otherwise the system is logout. The proposed Continuous User Biometric Authentication (CUBA) System is based on free text input from keyboard. There is no restriction on input data during Enrolment, Verification, and Identification phase. Unsupervised One-class Support Vector Machine is used to classify the authenticated user’s input from all the other inputs. This continuous authentication system can be used in many areas like in Un-proctored online examination systems, Intrusion & Fraud Detection Systems, Areas where user alertness is required for entire period e.g. Controlling Air Traffic etc.

scholarly journals Continuous User Authentication Featuring Keystroke Dynamics Based on Robust Recurrent Confidence Model and Ensemble Learning Approach

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 156177-156189
Author(s):  
Anum Tanveer Kiyani ◽  
Aboubaker Lasebae ◽  
Kamran Ali ◽  
Masood Ur Rehman ◽  
Bushra Haq
Keyword(s):  
Ensemble Learning ◽  
User Authentication ◽  
Learning Approach ◽  
Keystroke Dynamics ◽  
Continuous User

scholarly journals THE PROBLEMS OF INFORMATION DEFENCE IN DIAGNOSIS INTELLIGENT SYSTEMS OF MICROPROCESSOR DEVICES

2014 ◽  
pp. 46-53
Author(s):  
Viktor Lokazyuk ◽  
Oksana Pomorova
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Intelligent Systems ◽  
Intelligent System ◽  
User Authentication ◽  
Keystroke Dynamics ◽  
Artificial Neural

The method for protection of diagnosis intelligent system of microprocessor devices is represented in the paper. This method based on background authentication of the user in the process of keyboarding. The user’s keystroke dynamics characteristics are the means of authentication. For realization of the user authentication method uses the artificial neural networks of ART2 architecture.

Sign in / Sign up

Export Citation Format

Share Document