DNN controlled adaptive front-end for replay attack detection systems

Buddhi Wickramasinghe, Eliathamby Ambikairajah, Vidhyasaharan Sethu, Julien Epps, Haizhou Li, Ting Dang

Abstract: Highlights·Conventional methods fall short in detecting replay spoofing attacks effectively.·Auditory-based dynamic filters can detect artefacts in high-quality replayed signals.·Deep neural networks can adaptively learn filter traits based on the application.·Auditory concepts and deep learning combined may generalize replay countermeasures.