Biometric Authentication Using Convolutional Neural Networks

Kuznetsov, Alexandr; Oleshko, Inna; Chernov, Kyrylo; Bagmut, Mykhaylo; Polishchuk, Liudmyla

doi:10.1007/978-3-030-58359-0_6

Cited by 7 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An adversary gained access to T-server Mobile and databases by using a brute-force logon technique [35]. Attackers also use deception assaults, in which they construct a false biometric sample that is similar enough to the real one to fool the system into granting access [36]. It is also essential to note that biometric systems are susceptible to social engineering attacks, in which a perpetrator manipulates or fools a user into divulging sensitive information.…”

Section: Different Attacks On Biometric Authentication Modelsmentioning

confidence: 99%

Extraction of Hidden Authentication Factors from Possessive Information

Nanglae

Yakubu

Bhattarakosol

2023

JSAN

View full text Add to dashboard Cite

Smartphones have emerged as a ubiquitous personal gadget that serve as a repository for individuals’ significant personal data. Consequently, both physiological and behavioral traits, which are classified as biometric technologies, are used in authentication systems in order to safeguard data saved on smartphones from unauthorized access. Numerous authentication techniques have been developed; however, several authentication variables exhibit instability in the face of external influences or physical impairments. The potential failure of the authentication system might be attributed to several unpredictable circumstances. This research suggests that the use of distinctive and consistent elements over an individual’s lifespan may be employed to develop an authentication classification model. This model would be based on prevalent personal behavioral biometrics and could be readily implemented in security authentication systems. The biological biometrics acquired from an individual’s typing abilities during data entry include their name, surname, email, and phone number. Therefore, it is possible to establish and use a biometrics-based security system that can be sustained and employed during an individual’s lifetime without the explicit dependance on the functionality of the smartphone devices. The experimental findings demonstrate that the use of a mobile touchscreen as the foundation for the proposed verification mechanism has promise as a high-precision authentication solution.

show abstract

Section: Different Attacks On Biometric Authentication Modelsmentioning

confidence: 99%

Extraction of Hidden Authentication Factors from Possessive Information

Nanglae

Yakubu

Bhattarakosol

2023

JSAN

View full text Add to dashboard Cite

show abstract

“…The rapid development of artificial intelligence technologies in recent years has significantly improved the quality of automatic image recognition, making it possible to segment complex scenes and highlight objects of interest both in the video stream and in data from other sensors, for example, scanning laser rangefinders [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

The Method of Observing Moving Objects

Mezin,

Kuchuk,

Lyashova

et al. 2024

CNCS

View full text Add to dashboard Cite

The article analyzes known algorithms for tracking moving objects. Based on an analysis of known algorithms for tracking moving objects, it was concluded that the best tracking quality in problems with a large number of observed objects is achieved by solutions built on the basis of probabilistic and hierarchical methods. Each of them has complementary advantages, which creates prospects for creating new algorithmic solutions built on the synergy of these approaches. The main task of promising tracking methods is that they should provide ease of scaling with an increase in the number of moving objects that need to be monitored, localize objects in three-dimensional space, and also be able to work with heterogeneous sensors. This approach has both purely technical advantages and those related to the availability of microelectronics components in modern geopolitical realities.

show abstract

“…The information component of the problem under consideration is analyzed in articles [11,12]. Aspects of the fight against complex cybercrimes are discussed in articles [13,14]. Issues of using neural networks in research related to national security are discussed in articles [15,16].…”

Section: Introductionmentioning

confidence: 99%

Practical Principles of Integrating Artificial Intelligence Into the Technology of Regional Security Predicting

Shefer,

Laktionov,

Pents

et al. 2024

A.I.S.

View full text Add to dashboard Cite

Objective. The aim is to enhance the efficiency of diagnostics for determining the level of air attack safety through the practical integration principles of artificial intelligence. Methodology. Models and technologies for safety diagnostics of the region (territorial community) have been explored. The process of building an artificial intelligence model requires differentiation of objects at a level to accumulate assessments-characteristics of aerial vehicles. The practical integration principles of artificial intelligence into the forecasting technology are based on the Region Safety Index, used for constructing machine learning models. The optimal machine learning model of the proposed approach is selected from a list of several models. Results. A technology for predicting the level of regional safety based on the Safety Index has been developed. The recommended optimal model is the Random Forest model ([('max_depth', 13), ('max_features', 'sqrt'), ('min_samples_leaf', 1), ('min_samples_split', 2), ('n_estimators', 79)]), demonstrating the most effective quality indicators of MAE; MAX; RMSE 0.005; 0.083; 0.0139, respectively. Scientific Novelty. The proposed approach is based on a linear model of the Region Safety Index, which, unlike existing ones, takes into account the interaction of factors. This allows for advantages of the proposed method over existing approaches in terms of the root mean square error of 0.496; 0.625, respectively. In turn, this influences the quality of machine learning models. Practical Significance. The proposed solutions are valuable for diagnosing the level of safety in the region of Ukraine, particularly in the context of air attacks.

show abstract

Biometric Authentication Using Convolutional Neural Networks

Cited by 7 publications

References 8 publications

Extraction of Hidden Authentication Factors from Possessive Information

Extraction of Hidden Authentication Factors from Possessive Information

The Method of Observing Moving Objects

Practical Principles of Integrating Artificial Intelligence Into the Technology of Regional Security Predicting

Contact Info

Product

Resources

About