Modified Distance Metric That Generates Better Performance For The Authentication Algorithm Based On Free-Text Keystroke Dynamics

Iapa, Augustin-Catalin; Creţu, Vladimir

doi:10.1109/saci51354.2021.9465601

Cited by 5 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These systems are used for continuous authentication and are often used to defend against keystroke-injection attacks. The evaluation of accuracy and performance in free-text keystroke dynamics is an ongoing area of investigation; researchers are actively developing methods to minimize error rates in this domain [46], while other researchers have explored the application of cGAN networks to generate fake keystroke dynamics patterns with the intention of deceiving keystroke-authentication systems [47]. Given the growing need for remote learning, continuous authentication with keystroke dynamics was implemented and performed very effectively [48], although keystroke dynamics has significant inaccuracies when applied to RDP (remote desktop protocol) and VNC (virtual network computing) systems, resulting in poor or non-functioning operation.…”

Section: Keystroke Dynamics and Its Circumventionmentioning

confidence: 99%

A Deep-Learning-Based Approach to Keystroke-Injection Payload Generation

Gurčinas,

Dautartas,

Janulevičius

et al. 2023

Electronics

View full text Add to dashboard Cite

Investigation and detection of cybercrimes has been in the spotlight of cybersecurity research for as long as the topic has existed. Modern methods are required to keep up with the pace of the technology and toolset used to facilitate these crimes. Keystroke-injection attacks have been an issue due to the limitations of hardware and software up until recently. This paper presents comprehensive research on keystroke-injection payload generation that proposes the use of deep learning to bypass the security of keystroke-based authentication systems focusing on both fixed-text and free-text scenarios. In addition, it specifies the potential risks associated with keystroke-injection attacks. To ensure the legitimacy of the investigation, a model is proposed and implemented within this context. The results of the implemented implant model inside the keyboard indicate that deep learning can significantly improve the accuracy of keystroke dynamics recognition as well as help to generate effective payload from a locally collected dataset. The results demonstrate favorable accuracy rates, with reported performance of 93–96% for fixed-text scenarios and 75–92% for free-text. Accuracy across different text scenarios was achieved using a small dataset collected with the proposed implant model. This dataset enabled the generation of synthetic keystrokes directly within a low-computation-power device. This approach offers efficient and almost real-time keystroke replication. The results obtained show that the proposed model is sufficient not only to bypass the fixed-text keystroke dynamics system, but also to remotely control the victim’s device at the appropriate time. However, such a method poses high security risks when deploying adaptive keystroke injection with impersonated payload in real-world scenarios.

show abstract

Section: Keystroke Dynamics and Its Circumventionmentioning

confidence: 99%

A Deep-Learning-Based Approach to Keystroke-Injection Payload Generation

Gurčinas,

Dautartas,

Janulevičius

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…They made a novel feature engineering method which creates an image similar to transition matrices.A convolution neural network (CNN) with cutout achieves the best results for this image-like feature. Augustin-Catalin Iapa; Vladimir-Ioan Cretu [14] aimed to analyze the possibilities of increasing the efficiency of an authentication algorithm based on keystroke dynamics by reducing the value of the Equal Error Rate (EER). They modified the Manhattan distance calculation formula to generates better performances, EER was improved by 38.53%, so the EER value became 3.27%, compared to 5.32% obtained with the classic Manhattan formula.…”

Section: Related Workmentioning

confidence: 99%

Fixed-Text vs. Free-Text Keystroke Dynamics for User Authentication

Zeid¹,

ElKamar²,

Hassan³

2022

Engineering Research Journal - Faculty of Engineering (Shoubra)

View full text Add to dashboard Cite

There are many physical biometrics such as iris patterns and fingerprints. There are also interactive gestures like how a person types on a keyboard, moves a mouse, holds a phone, or even taps a touch screen. Keystroke dynamics or typing dynamics is an automatic method that confirms the identity of an individual based on the manner and the way of the user typing on a keyboard. There are two types of keystroke systems, Fixed-text system, and free-text system and each of them has it is own importance. In this research paper, we are investigating the possibility of classifying individuals using features extracted from their keystroke dynamics with two different datasets: (1) fixed-text dataset with different difficulty levels and (2) free-text dataset with no restrictions what a user types on the keyboard. Investigation was done using several classification techniques: RandomForest (RF), Support Vector Machines (SVM), BayesNet (BN), and K-Nearest Neighbors (KNN). The highest accuracy achieved with the fixed-text dataset was 98.8% using RF for classification while the highest achieved accuracy with the freetext dataset was 87.58 % using RF classifier.

show abstract

“…They used keystroke data of 300 volunteers to verify the model, and the experimental result was 10.4%. In 2021, Iapa et al [3] modified the distance measure, collected 200,000 experimental data from 80 volunteers, and obtained an EER of 3.27% -5.32%.…”

Section: Related Workmentioning

confidence: 99%

ACBM: attention-based CNN and Bi-LSTM model for continuous identity authentication

Mao

Wang

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

With the evolution of network attack methods, implicit continuous identity authentication technology has attracted more and more attention. Among them, keystroke dynamics is widely used because it does not need the assistance of devices other than keyboards. In this paper, we propose a keystroke dynamic identity authentication model based on deep learning. This model combines convolutional neural network (CNN), bi-directional Long Short-Term Memory (BI-LSTM), and the attention mechanism. Unlike most existing models that only use keystroke time as the feature vector, this model uses keystroke content and keystroke time as the feature vector. First, CNN is used to process feature vectors. Then the normalized vector is input into the bi-LSTM network for training. The model in this paper is tested using Buffalo open data set. The results show that FRR (False Reject Rate), FAR (False Accept Rate), and EER(Equal Error Rate) are 3.09%, 3.03%, and 4.23%, respectively. The validity and accuracy of the model in continuous identity authentication are proved.

show abstract

Modified Distance Metric That Generates Better Performance For The Authentication Algorithm Based On Free-Text Keystroke Dynamics

Cited by 5 publications

References 22 publications

A Deep-Learning-Based Approach to Keystroke-Injection Payload Generation

A Deep-Learning-Based Approach to Keystroke-Injection Payload Generation

Fixed-Text vs. Free-Text Keystroke Dynamics for User Authentication

ACBM: attention-based CNN and Bi-LSTM model for continuous identity authentication

Contact Info

Product

Resources

About