Banca de DEFESA: MARCELO DAMASCENO DE MELO

Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
DISCENTE: MARCELO DAMASCENO DE MELO
DATA: 07/03/2016
HORA: 14:00
LOCAL: Sala de reunioes do DIMAP
TÍTULO:

Verificação de Usuários através de Biometrias canceláveis comportamentais. 


PALAVRAS-CHAVES:
Behavioural Biometrics, Cancelable Biometrics, Template Protection, Non-invertible Functions, User Verification, Mobile Authentication, Key Length, Key Storage

PÁGINAS: 84
GRANDE ÁREA: Ciências Exatas e da Terra
ÁREA: Ciência da Computação
SUBÁREA: Metodologia e Técnicas da Computação
ESPECIALIDADE: Sistemas de Informação
RESUMO:
The verification of user identity is a faced daily problem to people or system that authorize the acess of people taking account the physical and document characteristics.
However, efforts need to be spend to resolve related questions to accuracy of verification system and in the falsification of objects and personal information.
Thus, biometrics proposes minimize and resolve these difficulties.
Unfortunately, the substitution of biometric traces in the case of compromise is difficult.
Hence, the use of non-invertible functions is proposed to distort the biometric traces.
Consequently, this procedures allows that biometric templates becomes cancelable or revocable.

This thesis analysis some solution to user verification using cancelable behavioural biometrics.
The analysed solutions are based on the use of single classifiers and ensemble system to resolve the user verification problem.
In addition, this thesis analysis the use of multiple cancelable templates using ensemble system (Multiple-Privacy Protection Schemes).
This thesis also presents a discussion of key impact in a cancelable function.
Thus, we show a empiric study of use of single or different key values to enrolled users.
Moreover, a study of the impact of key length is discussed based on the accuracy of biometric system.
Based on the results, it is discussed the generation and storage of cancelable keys in mobile devices.

In summary, we have demonstrated that the use of a transformation function usually provides similar or better performance than Original biometric data, except in BioHashing function.
In addition, the use of multiple protected templates processed by ensemble system outperformed the previous results in single classifiers and ensemble system.
Moreover, we showed that biometric system with cancelable templates preserves the user privacy, i.e, it provides lower False Acceptance and False Rejection Errors in Unknown Key attacks and similar performance to unprotected biometric samples in Known Key Attacks.
Based on key length experiments, we observe a perceptible continuous improvement when the key increases in Interpolation and BioHashing method in both key knowledge attacks.
In contrast, Double Sum have minor improvements but the most important is the performance does not decrease when the key increases.
In conclusion, based on our findings, we proposes the use of a key generated by system to authenticate users in mobile devices using cancelable biometric templates.

MEMBROS DA BANCA:
Presidente - 1350250 - ANNE MAGALY DE PAULA CANUTO
Interno - 2212166 - BENJAMIN RENE CALLEJAS BEDREGAL
Externo ao Programa - 4351681 - JOAO CARLOS XAVIER JUNIOR
Externo à Instituição - ANDRÉ CARLOS PONCE DE LEON FERREIRA DE CARVALHO - USP
Externo à Instituição - GEORGE DARMITON DA CUNHA CAVALCANTI - UFPE
Notícia cadastrada em: 14/02/2016 20:37
SIGAA | Superintendência de Informática - (84) 3215-3148 | Copyright © 2006-2017 - UFRN - sigaa02-producao.info.ufrn.br.sigaa02-producao