Geri Dön

Producing secure multimodal biometric descriptors using artificial neural networks

Başlık çevirisi mevcut değil.

  1. Tez No: 716581
  2. Yazar: RAGHAD SAEED HASAN
  3. Danışmanlar: DR. ÖĞR. ÜYESİ DOĞU ÇAĞDAŞ ATİLLA, DR. ÖĞR. ÜYESİ ÇAĞATAY AYDIN
  4. Tez Türü: Doktora
  5. Konular: Elektrik ve Elektronik Mühendisliği, Electrical and Electronics Engineering
  6. Anahtar Kelimeler: Belirtilmemiş.
  7. Yıl: 2021
  8. Dil: İngilizce
  9. Üniversite: Altınbaş Üniversitesi
  10. Enstitü: Lisansüstü Eğitim Enstitüsü
  11. Ana Bilim Dalı: Elektrik ve Bilgisayar Mühendisliği Ana Bilim Dalı
  12. Bilim Dalı: Elektrik Bilim Dalı
  13. Sayfa Sayısı: 103

Özet

With the growing importance and sensitivity of information and digital services being provided for different users, the need for better protection schemes has surfaces, according to the sensitivity of traditional secret-based techniques to simple attacks, such as shoulder surfing and guessing. Biometric authentication has emerged as a solution to these limitations, according to the high robustness of biometric features and their high availability. Combined with anti-spoofing methods that the biometric collection sensors are equipped with, biometric authentication has been able to provide better security to the protected systems. Furthermore, multimodal biometric authentication has been widely investigated in recent years to improve the accuracy of biometric authentication, by using multiple biometric templates to recognize a candidate. Despite the significant improvement of recognition accuracy, multimodal biometric authentication does not contribute towards securing the vulnerabilities of these systems. Several of these attacks occur during the transportation of the information over the network, which encouraged the proposal of methods that deny such attacks. However, existing methods require additional processing to detect these attacks, which increases the complexity of the system. Hence, a new method is proposed in this study to produce a fixed-size descriptor for each candidate based on their face and fingerprint templates. The proposed method also takes into consideration the timestamp in which the template is collected and a system identifier, so that, the descriptor becomes invalid after a predefined period of time and a descriptor generated at a certain system fails to authenticate of another, even if these descriptors are generated at the same timestamp. The proposed method uses a Convolutional Neural Network (CNN) to generated a 512-value descriptor, which is used to authenticate the candidate by simply measuring the Euclidean distance to the model descriptor. The embedding of the timestamp and system identifier in the descriptor allows the validation of these parameters in the same measurement, i.e. no additional processing is required. In addition to the high recognition accuracy achieved by the proposed method, with 99.41% and 99.32% accuracies using two different setups, the proposed method has also been able to maintain the privacy of the users, based on the one-way computations in the CNN.

Özet (Çeviri)

With the growing importance and sensitivity of information and digital services being provided for different users, the need for better protection schemes has surfaces, according to the sensitivity of traditional secret-based techniques to simple attacks, such as shoulder surfing and guessing. Biometric authentication has emerged as a solution to these limitations, according to the high robustness of biometric features and their high availability. Combined with anti-spoofing methods that the biometric collection sensors are equipped with, biometric authentication has been able to provide better security to the protected systems. Furthermore, multimodal biometric authentication has been widely investigated in recent years to improve the accuracy of biometric authentication, by using multiple biometric templates to recognize a candidate. Despite the significant improvement of recognition accuracy, multimodal biometric authentication does not contribute towards securing the vulnerabilities of these systems. Several of these attacks occur during the transportation of the information over the network, which encouraged the proposal of methods that deny such attacks. However, existing methods require additional processing to detect these attacks, which increases the complexity of the system. Hence, a new method is proposed in this study to produce a fixed-size descriptor for each candidate based on their face and fingerprint templates. The proposed method also takes into consideration the timestamp in which the template is collected and a system identifier, so that, the descriptor becomes invalid after a predefined period of time and a descriptor generated at a certain system fails to authenticate of another, even if these descriptors are generated at the same timestamp. The proposed method uses a Convolutional Neural Network (CNN) to generated a 512-value descriptor, which is used to authenticate the candidate by simply measuring the Euclidean distance to the model descriptor. The embedding of the timestamp and system identifier in the descriptor allows the validation of these parameters in the same measurement, i.e. no additional processing is required. In addition to the high recognition accuracy achieved by the proposed method, with 99.41% and 99.32% accuracies using two different setups, the proposed method has also been able to maintain the privacy of the users, based on the one-way computations in the CNN.

Benzer Tezler

  1. Genetik algoritmalarla güvenli veri iletimi için şifreleme anahtarı üretimi

    Encryption key generation for secure data transmission with genetic algorithms

    GAMZE KILAVUZ DEMİR

    Yüksek Lisans

    Türkçe

    Türkçe

    2024

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolGazi Üniversitesi

    Adli Bilişim Ana Bilim Dalı

    PROF. DR. MUSTAFA ALKAN

  2. Enerjisini iklimden üreten akıllı evler

    Producing energy from climate smart homes

    MAHYAR SHAHBAZİ JAMALABAD

    Yüksek Lisans

    Türkçe

    Türkçe

    2014

    Mimarlıkİstanbul Aydın Üniversitesi

    Mimarlık Ana Bilim Dalı

    PROF. DR. AYŞE BİLGE IŞIK

  3. Secure communication via partial synchronization of nonlinear systems

    Doğrusal olmayan sistemlerin kısmi senkronizasyonu ile güvenli haberleşme

    ZEKERİYA SARI

    Yüksek Lisans

    İngilizce

    İngilizce

    2016

    Elektrik ve Elektronik MühendisliğiDokuz Eylül Üniversitesi

    Elektrik-Elektronik Mühendisliği Ana Bilim Dalı

    YRD. DOÇ. DR. SERKAN GÜNEL

  4. Designing an RNG for secure data communication with WISP

    WISP ile güvenli veri transferi için random sayı üreteci tasarlanması

    CEM KÖSEMEN

    Yüksek Lisans

    İngilizce

    İngilizce

    2019

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolDokuz Eylül Üniversitesi

    Bilgisayar Mühendisliği Ana Bilim Dalı

    DOÇ. DR. GÖKHAN DALKILIÇ

  5. Gıdaların soğuk zincir lojistiği

    Cold chain logistics of foods

    GİRAY SARISOY

    Yüksek Lisans

    Türkçe

    Türkçe

    2011

    İşletmeBahçeşehir Üniversitesi

    Tedarik Zinciri Yönetimi ve Lojistik Yönetimi Ana Bilim Dalı

    PROF. DR. MEHMET TANYAŞ