Secure cognitive recognition: brain-based biometric cryptosystems using EEG
Cognitive biometric recognition systems, based on the exploitation of nervous tissues' responses as identifiers, have recently attracted an always-growing interest from the scientific community, thanks to the several advantages they could offer with respect to traditional biometric approaches based on physical or behavioral characteristics, such as fingerprint, face, signature, and so forth. Biosignals are in fact much more robust against presentation attacks, being hard, if not impossible, to covertly capture and then replicate them. Liveness detection is also inherently provided. Nevertheless, their usage could expose several sensitive information regarding people's health and capability, making the system prone to function creep issues. With the aim of guaranteeing proper privacy and security to the users of the such systems, different general cryptosystem architectures for cognitive biometric traits are therefore presented in this chapter. Their effectiveness is evaluated by applying the proposed approaches to brain signals sensed through electroencephalography (EEG). A multi-session EEG dataset comprising recordings taken in three distinct occasions from each of 50 subjects is employed to perform the reported experimental test.
Secure cognitive recognition: brain-based biometric cryptosystems using EEG, Page 1 of 2
< Previous page Next page > /docserver/preview/fulltext/books/sc/pbse004e/PBSE004E_ch14-1.gif /docserver/preview/fulltext/books/sc/pbse004e/PBSE004E_ch14-2.gif