Machine and Deep Learning Applications to Mouse Dynamics for Continuous User Authentication

Siddiqui, Nyle; Dave, Rushit; Vanamala, Mounika; Seliya, Naeem

doi:10.3390/make4020023

Cited by 27 publications

(11 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Naïve Bayes can be split into three variants: Gaussian Naïve Bayes, Multinomial Naïve Bayes, and Bernoulli Naïve Bayes. Only the Gaussian Naïve Bayes and Multinomial Naïve Bayes were used since the Bernoulli variant deals with data with binary features (i.e., each feature can only take on two values) [19], [20]. The attempt to use the Multinomial variant resulted in an error due to the dataset not being able to assume the correct format for the variant to function properly.…”

Section: Resultsmentioning

confidence: 99%

Software Engineering and Applications

2023

View full text Add to dashboard Cite

Secure software engineering is crucial but can be time-consuming; therefore, methods that could expedite the identification of software weaknesses without reducing the process' efficacy would benefit the software engineering industry and thus benefit modern life. This research focuses on finding an efficient machine learning algorithm to identify software weaknesses from requirement specifications. The research uses the CWE repository and PROMISE_exp dataset for training. Keywords extracted using latent semantic analysis help map the CWE categories to PROMISE_exp. Naïve Bayes, support vector machine (SVM), decision trees, neural network, and convolutional neural network (CNN) algorithms were tested, with SVM and neural network producing reliable results. The research's unique contribution lies in the mapping technique and algorithm selection. It serves as a valuable reference for the secure software engineering community seeking to expedite the development lifecycle without compromising efficacy. Future work involves testing more algorithms, optimizing existing ones, and improving the training sets' accuracy.

show abstract

Section: Resultsmentioning

confidence: 99%

Software Engineering and Applications

2023

View full text Add to dashboard Cite

show abstract

“…Smartphone motion analysis supporting PIN-based authentication is proposed in [ 19 ]. Behavioral biometrics modalities such as keystroke and mouse dynamics often strengthen user authentication security in computer systems [ 20 , 21 ].…”

Section: Related Workmentioning

confidence: 99%

Online Signature Biometrics for Mobile Devices

Roszczewska,

Niewiadomska-Szynkiewicz

2024

Sensors

View full text Add to dashboard Cite

This paper addresses issues concerning biometric authentication based on handwritten signatures. Our research aimed to check whether a handwritten signature acquired with a mobile device can effectively verify a user’s identity. We present a novel online signature verification method using coordinates of points and pressure values at each point collected with a mobile device. Convolutional neural networks are used for signature verification. In this paper, three neural network models are investigated, i.e., two self-made light SigNet and SigNetExt models and the VGG-16 model commonly used in image processing. The convolutional neural networks aim to determine whether the acquired signature sample matches the class declared by the signer. Thus, the scenario of closed set verification is performed. The effectiveness of our method was tested on signatures acquired with mobile phones. We used the subset of the multimodal database, MobiBits, that was captured using a custom-made application and consists of samples acquired from 53 people of diverse ages. The experimental results on accurate data demonstrate that developed architectures of deep neural networks can be successfully used for online handwritten signature verification. We achieved an equal error rate (EER) of 0.63% for random forgeries and 6.66% for skilled forgeries.

show abstract

“…This lack of cybersecurity professionals is not limited to the government [16]. Additionally, automated systems such as authentication using machine learning are not enough to make up for this discrepancy [17], [18], [19]. Thus, considering the evident lack of cybersecurity professionals, it would be prudent for individuals to learn to protect themselves.…”

Section: Literature Reviewmentioning

confidence: 99%

Secure Arcade: A Gamified Defense Against Cyber Attacks

Loesch,

Hrastich,

Herbert

et al. 2023

IJCSIT

View full text Add to dashboard Cite

In modernity, we continually receive increasingly intricate technologies that allow us to increase our lives’ convenience and efficiency. Our technology, particularly technology available over the internet, is advancing at unprecedented speed. However, this speed of advancement allows those behind malicious attacks to have an increasingly easier time taking advantage of those who know little about computer security. Unfortunately, education in the computer security field is generally limited only to tertiary education. This research addresses this problem through a gamified web-based application that drives users to reach learning goals to help them become more vigilant internet users: 1. Learn and memorize general computer security terminology, 2. Become familiar with basic cryptography concepts, 3. Learn to recognize potential phishing scams via email quickly, and 4. Learn common attacks on servers and how to deal with them.

show abstract

Machine and Deep Learning Applications to Mouse Dynamics for Continuous User Authentication

Cited by 27 publications

References 38 publications

Software Engineering and Applications

Software Engineering and Applications

Online Signature Biometrics for Mobile Devices

Secure Arcade: A Gamified Defense Against Cyber Attacks

Contact Info

Product

Resources

About