Refine
Document Type
- Doctoral Thesis (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Keywords
Biometric recognition systems are part of our daily life. They enable
a user-convenient authentication alternative to passwords or tokens
as well as high security identity assessment for law enforcement and
border control. However, with a rising usage in general, fraudulent use increases as well. One drawback of biometrics in general is the lack of renewable biometric characteristics. While it is possible to change a password or token, biometric characteristics (e. g. the fingerprint) stays the same throughout a lifespan. Hence, biometric systems are required to ensure privacy protection in order to prevent misuse of sensitive data. In this context, this Thesis evaluates cryptographic solutions that enable storage and real time comparison of biometric data in the encrypted domain. Furthermore, long-term security is achieved by post-quantum secure mechanisms.In addition to those privacy concerns, presentation attacks targeting the capture device are threatening legit operations. Since no information about inner system modules are required to use a presentation attack instrument (PAI) at the capture device, also non-experts could attack the biometric system. Thus, presentation attack detection (PAD) modules are essential to distinguish between bona fide presentations
and attack presentations. In this regard, different methods for fingerprint PAD are analysed in this Thesis, including benchmarks on
several classifiers based on handcrafted features as well as deep learning techniques. The results show that the PAD performance depends
on material properties of the used PAI species in combination with the
captured data type. However, fusing multiple approaches enhances the
detection rates for both convenient and secure application scenarios.
Biometric systems have experienced a large development in recent
years since they are accurate, secure, and in many cases, more user
convenient than traditional credential-based access control systems. Inspite of their benefits, biometric systems are still vulnerable to attack presentations (APs), which can be easily launched by a fraudulentsubject without having a wide expert knowledge. This way, he/she can gain access to several applications, such as bank accounts and smartphone unlocking, where biometric systems are frequently deployed. In order to mitigate such threats and increase the security of biometric systems, the development of reliable Presentation Attack
Detection (PAD) algorithms is of utmost importance to the research
community.In the context of PAD, we explore in this Thesis different strategies and methods in order to improve the generalisation capability of PAD schemes. To that end, we propose the definition of a semantic common feature space which successfully discriminates bona fide presentations (BPs)1 from APs. In essence, this process is seeking for those significant features extracted from known PAI species samples that are observed in unknown PAI species. In addition, we explore several handcrafted techniques in order to build a reliable description of features per biometric characteristic studied. The experimental evaluation shows that a common feature space can be computed through the fusion between generative models and discriminative approaches. Remarkable detection performances for high-security thresholds lead to the construction of a convenient (i.e., low BP rejection rates or Bona fide Presentation Classification Error Rate (BPCER)) and secure (i.e., low AP acceptance rates or Attack Presentation Classification Error Rate (APCER)) PAD subsystem.