Anomaly detection approach to keystroke dynamics based user authentication

Ivannikova, Elena; David, Gil; Hämäläinen, Timo D.

doi:10.1109/iscc.2017.8024638

Cited by 14 publications

(13 citation statements)

References 19 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This also shows that the application of KDA to a system is very safe [14]. Then, the main reason for using KDA in this research is that it does not require expensive costs (low costs) and does not need any additional devices [14][15][16] (only uses the keyboard). This differentiates KDA with another Biometric Authentication which using adding devices (such as face or fingerprints) [17].…”

Section: Introductionmentioning

confidence: 66%

Combined scaled manhattan distance and mean of horner’s rules for keystroke dynamic authentication

2020

View full text Add to dashboard Cite

Account security was determined by how well the security techniques applied by the system were used. There had been many security methods that guaranteed the security of their accounts, one of which was Keystroke Dynamic Authentication. Keystroke Dynamic Authentication was an authentication technique that utilized the typing habits of a person as a security measurement tool for the user account. From several research, the average use in the Keystroke Dynamic Authentication classification is not suitable, because a user's typing speed will change over time, maybe faster or slower depending on certain conditions. So, in this research, we proposed a combination of the Scaled Manhattan Distance method and the Mean of Horner's Rules as a classification method between the user and attacker against the Keystroke Dynamic Authentication. The reason for using Mean of Horner's Rules can adapt to changes in values over time and based on the results can improve the accuracy of the previous method.

show abstract

Section: Introductionmentioning

confidence: 66%

Combined scaled manhattan distance and mean of horner’s rules for keystroke dynamic authentication

2020

View full text Add to dashboard Cite

show abstract

“…Similarly, a smaller proportion of research (25%) investigated combination characteristics. The following are the research areas where researchers are interested -(a) Improving accuracy through techniques such as feature fusion [99], [100], score fusion [101], [102], feature selection [103], [104], anomaly detection [105], [106], and others. (b) Domain adaptation for cross-device validation [107], [108], (c) Real-world dataset collected using IoTenabled device with typing patterns [109], some times data are being collected in different positions [110] through a variety of applications like arithmetic games [111], e-wallet [112], video clips for emotional changing [113], (d) Usability control specifically in active authentication where data are being captured continuously [114], to balance the device and application levels security, (e) Computation and energy consumption specifically in the area of a smartphone where battery power is limited [110], (f) Design some useful intelligent applications including auto-profiling user [40], disease prediction [32], age-restricted security control, genderspecific advertisement, password recovery mechanism [115].…”

Section: G Increasing Research Trend (Contribution To Ob2)mentioning

confidence: 99%

A Systematic Literature Review on Latest Keystroke Dynamics Based Models

et al. 2022

View full text Add to dashboard Cite

The purpose of this study is to conduct a comprehensive evaluation and analysis of the most recent studies on the implications of keystroke dynamics (KD) patterns in user authentication, identification, and the determination of useful information. Another aim is to provide an extensive and up-to-date survey of the recent literature and potential research directions to understand the present state-of-the-art methodologies in this particular domain that are expected to be beneficial for the KD research community. From January 1st, 2017 to March 13th, 2022, the popular six electronic databases have been searched using a search criterion ("keystroke dynamics" OR "typing pattern") AND ("authentication" OR "verification" OR "identification"). With this criterion, a total of nine thousand three hundred forty-eight results, including duplicates, were produced. However, one thousand five hundred forty-seven articles have been chosen after removing duplicates and preliminary screening. Due to insufficient information, only one hundred twentyseven high-quality quantitative research articles have been included in the article selection process. We compared and summarised several factors with multiple tables to comprehend the various methodologies, experimental settings, and findings. In this study, we have identified six unique KD-based designs and presented the status of findings toward an effective solution in authentication, identification, and prediction. We have also discovered considerable heterogeneity across studies in each KD-based design for desktops and smartphones separately. Finally, this paper found a few open research challenges and provided some indications for a deeper understanding of the issues and further study.

show abstract

“…This characteristic further confirms the practical feasibility of our authentication method. It is worth noticing that typical training set dimensions adopted in the related works are greater than a hundred samples [10][11][12]16]. Since the behavior of users is not necessarily repetitive, false negatives might be detected by the authentication system.…”

Section: Ba =mentioning

confidence: 99%

“…In this way, the user's drawing traits are used as a further authentication measure, beyond the secrecy of the PIN. Finally, keystroke dynamics information, describing the person's typing rhythm, can be used to enhance the security of alphanumeric passwords [11,12], or to provide free-text authentication [13].…”

Section: Introductionmentioning

confidence: 99%

Augmented PIN Authentication through Behavioral Biometrics

Nerini

Favarelli

Chiani

2022

Sensors

View full text Add to dashboard Cite

Personal Identification Numbers (PINs) are widely used today for user authentication on mobile devices. However, this authentication method can be subject to several attacks such as phishing, smudge, and side-channel. In this paper, we increase the security of PIN-based authentication by considering behavioral biometrics, specifically the smartphone movements typical of each user. To this end, we propose a method based on anomaly detection that is capable of recognizing whether the PIN is inserted by the smartphone owner or by an attacker. This decision is taken according to the smartphone movements, which are recorded during the PIN insertion through the built-in motion sensors. For each digit in the PIN, an anomaly score is computed using Machine Learning (ML) techniques. Subsequently, these scores are combined to obtain the final decision metric. Numerical results show that our authentication method can achieve an Equal Error Rate (EER) as low as 5% in the case of 4-digit PINs, and 4% in the case of 6-digit PINs. Considering a reduced training set, composed of solely 50 samples, the EER only slightly worsens, reaching 6%. The practicality of our approach is further confirmed by the low processing time required, on the order of fractions of milliseconds.

show abstract

Anomaly detection approach to keystroke dynamics based user authentication

Cited by 14 publications

References 19 publications

Combined scaled manhattan distance and mean of horner’s rules for keystroke dynamic authentication

Combined scaled manhattan distance and mean of horner’s rules for keystroke dynamic authentication

A Systematic Literature Review on Latest Keystroke Dynamics Based Models

Augmented PIN Authentication through Behavioral Biometrics

Contact Info

Product

Resources

About