The Gaze and Mouse Signal as Additional Source for User Fingerprints in Browser Applications

Fuhl, Wolfgang; Nikolai, Sanamrad,; Kasneci, Enkelejda

doi:10.5220/0011607300003417

Cited by 4 publications

(4 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fuhl et al [31] correlated the mouse movement trajectory to the human eye, which could be used as a fingerprint. However, these techniques need further validation and research.…”

Section: Overview Of Browser Fingerprint Researchmentioning

confidence: 99%

See 1 more Smart Citation

Browser Fingerprinting: Overview and Open Challenges

Hölbl,

Zadorozhny,

Welzer Družovec

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

The central concept of browser fingerprinting is the collection of device-specific information for identification or security purposes. This chapter provides an overview of the research conducted in the field of browser fingerprinting and presents an entry point for newcomers. Relevant literature is examined to understand the current research in the field of browser fingerprinting. Both research in the field of crafting browser fingerprints and protection against it is included. Finally, current research challenges and future research directions are presented and discussed.

show abstract

“…Fuhl et al [31] correlated the mouse movement trajectory to the human eye, which could be used as a fingerprint. However, these techniques need further validation and research.…”

Section: Overview Of Browser Fingerprint Researchmentioning

confidence: 99%

“…Research is already ongoing in this direction. Fuhl et al showed how to exploit user activity to create fingerprints and proved its practicality [31].…”

Section: Overview Of Browser Fingerprint Researchmentioning

confidence: 99%

Browser Fingerprinting: Overview and Open Challenges

Hölbl,

Zadorozhny,

Welzer Družovec

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…Using this, they demonstrated impostor detecting by analyzing how much the mouse cursor's position differs from the gaze's location. The fusion of data acquired from eye and mouse movements has also been investigated by Fuhl et al [7]. They noted that due to the strong correlation between mouse and eye movements, using the two methods together is not particularly efficient; though applied separately, it is reasonable, bringing comparable results.…”

Section: Related Workmentioning

confidence: 99%

“…• Regularization parameter C, values [5e-1, 1e-1, 5e-2, 55e-3] were tested; • Kernel coefficient gamma values [1,2,5,7,10] were also tested. Before the main training, hyperparameter finetuning was performed, which searched for the best parameters C and gamma values.…”

Section: Classifiersmentioning

confidence: 99%

User Authentication by Eye Movement Features Employing SVM and XGBoost Classifiers

Odya,

Górski,

Czyżewski

2023

IEEE Access

View full text Add to dashboard Cite

Devices capable of tracking the user's gaze have become significantly more affordable over the past few years, thus broadening their application, including in-home and office computers and various customer service equipment. Although such devices have comparatively low operating frequencies and limited resolution, they are sufficient to supplement or replace classic input interfaces, such as the keyboard and mouse. The biometric application we researched verifies a user's identity based on parameters acquired with a low-cost eye tracker. The use of the eye-tracking device in bank booths has many advantages, including the fact that eye trackers are contactless devices, which, especially in the light of the Covid pandemic, has increasing importance, in addition to providing a solution for confirming the liveness of the user. This paper describes an experiment in which 20 features extracted from eye movement data related mainly to saccades and fixations are used as a complementary biometric modality to authenticate clients at banking kiosks. Data were collected from 39 subjects while operating a banking system using engineered biometric kiosk prototypes. Authentication performance employing eye-movement tracking and parameterizing was compared for two classifiers: Support Vector Machine (SVM) and eXtreme Gradient Boosting (XGBoost). The results showed that the XGBoost-based classifier outperformed the SVM-based one regarding equal error rates (6.76% to 8% vs. 16.21 to 18.78%). Similar differences were obtained for true acceptance rates at different false acceptance rates (0.1 and 0.01), where the SVM-based classifier achieved a maximum of 81.08% and the XGBoost-based achieved 98.65%. Finally, prospects for the broader application of eye movement tracking as a biometric modality are discussed.INDEX TERMS Biometrics, gaze tracking, machine learning, support vector machines, XGBoost.

show abstract