Wyniki wyszukiwania - BazTech

1

Hybrid verification method based on finger-knuckle analysis and keystroke dynamics

Wesolowski T. E., Safaverdi H., Doroz R., Wrobel K.

Journal of Medical Informatics & Technologies

|

2017

|

Vol. 26

26--36

EN

The increasing number of personal data leaks becomes one of the most important security issues hence the need to develop modern computer user verification methods. In the article, a potential of biometric methods fusion for continuous user verification was assessed. A hybrid approach for user verification based on fusion of keystroke dynamics and knuckle images analysis was presented. Verification is performed by a classification module where an ensemble classifier was used to verify the identity of a user. A proposed classifier works on a database which comprises of knuckle images and keyboard events for keystroke dynamics. The proposed approach was tested experimentally. The obtained results confirm that the proposed hybrid approach performs better than methods based on single biometric feature hence the introduced method can be used for increasing a protection level of computer resources against forgers and impostors. The paper presents results of preliminary research conducted to assess the potential of biometric methods fusion.

2

The method and an examplary biometric system to verify users

Wojciechowska A., Choraś M., Kozik R.

Journal of Machine Construction and Maintenance - Problemy Eksploatacji

|

2017

|

no. 3

97--101

EN

Currently, multiple areas are restricted, and it is necessary to know PIN codes or a proper passwords. However, it is reasonable to use biometrics in order to verify users. This kind of systems are widely known and implemented in our daily life. In this article, the method and an exemplary system to verify users on the basis of palmprint biometrics is proposed. The paper includes the concept and of the device with a full description of all physical elements and algorithms implemented in the system. Finally, it also contains the accuracy results obtained from multiple experiments. The results show that this kind of user verification may be successful and should be developed. In the article, there are also some possible extensions and real-life implementations enumerated.

PL

W dzisiejszych czasach wiele miejsc pozostaje zabezpieczonych przed niepowołanym dostępem. Aby się tam dostać, należy podać numer PIN lub odpowiednie hasło. Rozsądnym wydaje się jednak wykorzystanie biometrii do weryfikowania użytkowników. Ten sposób sprawdzania tożsamości osób jest już dość szeroko stosowany w codziennym życiu. W artykule została zaprezentowana metoda oraz modelowy system, które wykorzystują dane biometryczne w postaci odcisków wewnętrznych części dłoni do weryfikacji użytkowników. Artykuł zawiera opis koncepcji działania urządzenia, wszystkich elementów systemu oraz zaimplementowanych algorytmów. Zawiera także wyniki skuteczności działania urządzenia otrzymane w wyniku przeprowadzonych eksperymentów. Otrzymane wyniki pokazują, że taki sposób weryfikacji użytkowników może być skuteczny i powinien być rozwijany. Omówiono również możliwe rozszerzenia przedstawionego systemu oraz jego możliwe zastosowania w życiu codziennym.

3

Application of Recurrent Neural Networks for User Verification based on Keystroke Dynamics

Kobojek P., Saeed K.

Journal of Telecommunications and Information Technology

|

2016

|

nr 3

80--90

EN

Keystroke dynamics is one of the biometrics techniques that can be used for the verification of a human being. This work briefly introduces the history of biometrics and the state of the art in keystroke dynamics. Moreover, it presents an algorithm for human verification based on these data. In order to achieve that, authors’ training and test sets were prepared and a reference dataset was used. The described algorithm is a classifier based on recurrent neural networks (LSTMand GRU). High accuracy without false positive errors as well as high scalability in terms of user count were chosen as goals. Some attempts were made to mitigate natural problems of the algorithm (e.g. generating artificial data). Experiments were performed with different network architectures. Authors assumed that keystroke dynamics data have sequence nature, which influenced their choice of classifier. They have achieved satisfying results, especially when it comes to false positive free setting.

4

User verification based on the analysis of keystrokes while using various software

Wesołowski T. E., Porwik P.

Journal of Medical Informatics & Technologies

|

2015

|

Vol. 24

13--22

EN

The article presents the new approach to a computer users verification. The research concerns an analysis of user’s continuous activity related to a keyboard used while working with various software. This type of analysis constitutes a type of free-text analysis. The presented method is based on the analysis of users activity while working with particular computer software (e.g. text editors, utilities). A method of computer user proﬁling is proposed and an attempt to intrusion detection based on k-NN classifier is performed. The obtained results show that the introduced method can be used in the intrusion detection and monitoring systems. Such systems are especially needed in medical facilities where sensitive data are processed.

5

Features reduction for computer user profiling based on mouse activity

Palys M., Wesołowski T. E.

Journal of Medical Informatics & Technologies

|

2015

|

Vol. 24

45--51

EN

The article is related to the computer systems security and to the problem of detecting the masqueraders, intruders who pretend to be legitimate users of computer systems, in particular. The research concerns computer user verification based on analysis of the mouse activity in computer system. The article presents an improvement of user verification method by introducing a new method of user proﬁling. The new user proﬁling method is based on the reduced number of features without the loss of information is introduced. The presented method of user proﬁling allows to simplify and speed up a user’s activity data analysis and is not causing the deterioration of intrusion detection. Additionally, a method of aggregating mouse activity basic events into a higher level events is described. This article presents the preliminary research and conclusions.

6

User profiling based on multiple aspects of activity in a computer system

Wesołowski T., Kudłacik P.

Journal of Medical Informatics & Technologies

|

2014

|

Vol. 23

121--130

EN

The paper concerns behavioral biometrics, specifically issues related to the verification of the identity of computer systems users based on user profiling. The profiling method for creating a behavioral profile based on multiple aspects of user activity in a computer system is presented. The work is devoted to the analysis of user activity in environments with a graphical user interface GUI. Mouse activity, keyboard and software usage are taken into consideration. Additionally, an attempt to intrusion detection based on the proposed profiling method and statistical measures is performed. Preliminary studies show that the proposed profiling method could be useful in detecting an intruder masquerading as an authorized user of the computer system. This article presents the preliminary research and conclusions.

7

Data clustering for the block profile method of intruder detection

Wesolowski T., Kudlacik P.

Journal of Medical Informatics & Technologies

|

2013

|

Vol. 22

209--216

EN

The paper concerns the problem of computer security and intrusion detection. In particular the problem of detecting the masqueraders – intruders who pretend to be authorized users of computer systems. The article presents an improvement of the block profile method of intruder detection for computer systems. As a base for the work the block profiles were taken and the clustering of the block profiles data was performed. The aim was to detect the masqueraders within the test data. The problem of computer security is particularly important in medical applications. Activities of intruder can distort the data stored in medical databases and analyzed by the medical expert systems or decision support systems and thus make it difficult to support the diagnosis of diseases. For this reason it is necessary protect the medical computer systems from unauthorized access. This article presents the preliminary research and conclusions.

8

The use of speech recognition and user verification in closed-circuit television systems

Kubanek M.

Elektronika : konstrukcje, technologie, zastosowania

|

2009

|

Vol. 50, nr 11

65-68

EN

Speech recognition systems, and the verification of persons on the basis of independent speech are widely used. In the speech recognition systems, we need to know what said examined person. These recognized words we can used to controlling any devices, which is controlled by computer. In a speaker verification, the prime interest is not in recognizing the words but determining who is speaking the words. In systems of speaker verification, a test of signal from an known speaker, user gives his own login, is compared to all known speaker signals in the set. If the vocal is the same and the user login is the same, the system accepts the user. In this work, it was proposed use speech recognition method to control the movement of the camera of closed-circuit television system, and use user verification method to log on to this system. Extraction of the audio features of person's speech is done using modified mechanism of cepstral speech analysis. Speech recognition is done using hidden Markov models. The main aim of this work, excepting the practical implementation of both methods, is show, how to modify the MFCC for speech recognition and user verification.

PL

Systemy rozpoznawania mowy i weryfikacji osób na podstawie mowy niezależnej są coraz częściej powszechnie używane. W systemach rozpoznawania mowy musimy wiedzieć, co zostało wypowiedziane przez testowaną osobę. Takie rozpoznane słowa można stosować do sterowania różnymi urządzeniami, kontrolowanymi przez komputer. W przypadku weryfikacji tożsamości nie jest ważne, co zostało wypowiedziane, ale kto to wypowiedział. W systemach weryfikacji tożsamości, gdzie każdy z zarejestrowanych użytkowników posiada swój własny unikalny login, zarejestrowana wypowiedź weryfikowanego użytkownika jest porównywana z wszystkimi wypowiedziami z bazy. Jeśli login się zgadza i charakterystyki głosowe są zgodne, wówczas system akceptuje weryfikowaną osobę. W artykule zaproponowano rozpoznawanie mowy do sterowania ruchem kamery przemysłowej, oraz weryfikację użytkownika na podstawie mowy niezależnej do logowania do systemu. Do ekstrakcji i kodowania charakterystyk głosowych zastosowano analizę cepstralną mowy. Jako aparat rozpoznający przyjęto ukryte modele Markowa. Głównym zadaniem tej pracy - oprócz oczywiście praktycznej implementacji opisanych metod - jest pokazanie, w jaki sposób należy zmodyfikować mechanizm analizy cepstralnej na potrzeby rozpoznawania mowy, a w jaki sposób na potrzeby weryfikacji tożsamości na podstawie mowy niezależnej.