Continuous Authentication on PCs using Artificial Immune System

Aljohani, Ohood; Aljohani, Nawaf; Bours, Patrick; Alsolami, Fahad

doi:10.1109/cais.2018.8442022

Cited by 8 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We plan to analyze energy and resource usage as future work and compare them with the existing studies [24,36]. Other studies also present novel classifiers like artificial immune systems [37] or deep learning models [12], providing additional opportunities for comparison. Evidence on intrusion detection also showed that two-stage systems increase accuracy without compromising efficiency [38].…”

Section: Discussionmentioning

confidence: 99%

Comparing Machine Learning Classifiers for Continuous Authentication on Mobile Devices by Keystroke Dynamics

et al. 2021

View full text Add to dashboard Cite

Continuous authentication (CA) is the process to verify the user’s identity regularly without their active participation. CA is becoming increasingly important in the mobile environment in which traditional one-time authentication methods are susceptible to attacks, and devices can be subject to loss or theft. The existing literature reports CA approaches using various input data from typing events, sensors, gestures, or other user interactions. However, there is significant diversity in the methodology and systems used, to the point that studies differ significantly in the features used, data acquisition, extraction, training, and evaluation. It is, therefore, difficult to establish a reliable basis to compare CA methods. In this study, keystroke mechanics of the public HMOG dataset were used to train seven different machine learning classifiers, including ensemble methods (RFC, ETC, and GBC), instance-based (k-NN), hyperplane optimization (SVM), decision trees (CART), and probabilistic methods (naïve Bayes). The results show that a small number of key events and measurements can be used to return predictions of user identity. Ensemble algorithms outperform others regarding the CA mobile keystroke classification problem, with GBC returning the best statistical results.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparing Machine Learning Classifiers for Continuous Authentication on Mobile Devices by Keystroke Dynamics

et al. 2021

View full text Add to dashboard Cite

show abstract

“…There are limited studies that apply artificial immune systems to continuous authentication in smartphones. The work of [19] demonstrated that NSA is an approach that is very appropriate for continuous authentication for PCs. The negative selection method can regularly track any changes in the environment, depending on the computer system owner's interaction.…”

Section: U=s∪n and S∩n=∅mentioning

confidence: 99%

“…The researchers included both mouse, keystroke users' biometric activities and evaluated the suggested NS's precision; the highest reported accuracy was 99.7%. To the researchers' knowledge, the first continuous authentication method that is based on the AIS class of algorithms was by [20]. They proposed a CA method based on AIS using the Clonal Selection (CS) algorithm for smartphones.…”

Section: U=s∪n and S∩n=∅mentioning

confidence: 99%

Adaptive Continuous Authentication System for Smartphones using Hyper Negative Selection and Random Forest Algorithms

Alharbi¹,

Marie²

2021

IJACSA

View full text Add to dashboard Cite

As smartphones have become a part of our daily lives, including payment and banking transactions; therefore, increasing current data and privacy protection models is essential. A continuous authentication model aims to track the smartphone user's interaction after the initial login. However, current continuous authentication models are limited due to dynamic changes in smartphone user behavior. This paper aims to enhance smartphone user privacy and security using continuous authentication based on touch dynamics by proposing a framework for smartphone devices based on user touch behavior to provide a more accurate and adaptive learning model. We adopt a hybrid model based on the Hyper Negative Selection Algorithm (HNSA) as an artificial immune system (AIS) and the random forest ensemble classifier to instantly classify a user behavior. With the new approach, a decision model could detect normal/abnormal user behavior and update a user profile continuously while using his/her smartphone. The proposed approach was compared with the v-detector and HNSA, where it shows a high average accuracy of 98.5%, a low false alarm rate, and an increased detection rate. The new model is significant as it could be integrated with a smartphone to increase user privacy instantly. It is concluded that the proposed approach is efficient and valuable for smartphone users to increase their privacy while dynamic user behaviors evolve to change.

show abstract

Securing Smart Offices Through an Intelligent and Multi-device Continuous Authentication System

Sánchez

Celdrán

Maimó

et al. 2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

Continuous Authentication on PCs using Artificial Immune System

Cited by 8 publications

References 15 publications

Comparing Machine Learning Classifiers for Continuous Authentication on Mobile Devices by Keystroke Dynamics

Comparing Machine Learning Classifiers for Continuous Authentication on Mobile Devices by Keystroke Dynamics

Adaptive Continuous Authentication System for Smartphones using Hyper Negative Selection and Random Forest Algorithms

Securing Smart Offices Through an Intelligent and Multi-device Continuous Authentication System

Contact Info

Product

Resources

About