Real-Time Behavioral Biometric Information Security System for Assessment Fraud Detection

Subash, Aditya; Song, Insu

doi:10.1109/icoco53166.2021.9673568

Cited by 7 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…x x [23] x [42] x [25] x x x [43] x x [44] x OLP [21] x [26] x x x x x [45] x x [16] x x x x VL [46] x The flexibility of authentication systems can be improved by adding diverse sets of authenticators for different scenarios [47]. Face and keystroke dynamic authenticators are supported by the majority of the surveyed works while other features (i.e., fingerprint, mouse movement, speech, etc.)…”

Section: A Authenticatorsmentioning

confidence: 99%

“…Table 2 provides the overview of authentication process in the surveyed paper and what authenticators are used for identity assurance and authorship assurance. Behaviour analysis [40] Face, Voice Writing/Plagiarism detection [41] Face, Keystroke Face, Keystroke [23] Face Face [42] Keystroke Keystroke [25] Face, Fingerprint, Keystroke [43] Face Eye-Gaze [44] Keystroke OLP [21] Keystroke Keystroke [26] Face, Mouse, Keystroke, Touch, Voice [45] Keystroke Keystroke [16] Face, Keystroke, Voice Behaviour analysis, Computer monitoring VL [46] Face Face tracking…”

Section: B Authentication Processmentioning

confidence: 99%

“…The various ML techniques are utilised to analyse videos, images, sounds, etc. [24,36,38,42]. This section discusses the different types of machine learning techniques used for feature detection and verification in authentication systems.…”

Section: Machine Learning In Authentication Processmentioning

confidence: 99%

“…For keystroke recognition, Subash and Song [42] compare the authentication accuracy with different classification algorithms: Multi-Perceptron (MLP) algorithm [54], CNN [55], Naïve Bayes (NB) [56], and Decision Tree (DT) [56] to find the best classification methods and proposed architectures in their study. The combination of CNN and Recurrent Neural Network (RNN) models has been applied to learn the personal keystroke input for continuous authentication to improve the performance of authentication accuracy [16].…”

Section: ) Verification/classificationmentioning

confidence: 99%

“…Haytom, Rosenberger, Charrier, Zhu and Regnier [41] activates keystroke dynamics only when the input text is longer than the equivalent of one page of content; otherwise, the face is the main user-verifying authenticator. The engagement between users and online learning courses is also considered as contextual information to detect abnormal behaviour and build the student's profile [39,42,45]. For example, to build a more comprehensive template for keystroke dynamics, the length of words, repetition of the word and the number of words found in the student's writing are considered [21].…”

Section: Contextual Informationmentioning

confidence: 99%

See 4 more Smart Citations

A Comprehensive Survey of Context-Aware Continuous Implicit Authentication in Online Learning Environments

et al. 2023

View full text Add to dashboard Cite

User authentication is crucial in the digital learning environment to preserve the integrity and reliability of the learning process. Implicit authentication using biometrics has been proposed to improve the user experience while resolving the issues that password dominant authentication faces. Implicit authentication does not require explicit user actions as it is a background process that implicitly acquires a user's identifying information through sensors embedded within the authenticating devices. To accommodate a variety of user contexts, context-aware implicit authentication has gained attention especially in the mobile device domain, but it has not been fully explored in digital learning environments. This study is motivated to determine how implicit authentication can observe students' behaviour without causing disruption to the learning activity. The study provides a structured systematic review of the existing literature to identify and discuss the structure of context-aware continuous implicit authentication systems and future directions. The study found that requirements in the future will be: 1) to consider diverse authenticators to cover all possible user interactions with online learning environments, including coverage of course participants not engaged with online exams; 2) to investigate template adaptation to overcome template ageing issues with biometrics; and 3) to explore evaluation approaches of context-aware implicit authentication systems.

show abstract