Generalized Spoof Detection and Incremental Algorithm Recognition for Spoofing Voice

Abstract

Highly deceptive deep-fake technologies have caused much controversy, e.g., artificial intelligence-based software can automatically generate nude photos and deep-fake images of Obama, Putin, and other political figures. This brings considerable threats to both individuals and society. In addition to video and image forgery, audio forgery poses many hazards but lacks sufficient attention. Furthermore, existing work has only focused on voice spoof detection, neglecting the identification of spoof algorithms. It is of great value to recognize the algorithm for synthesizing spoofing voices in traceability. This study presents a system combining voice-spoof detection and algorithm recognition. In contrast, the generalizability of the spoof detection model is discussed from the perspective of embedding space and decision boundary to face the spoofing voice attacks generated by spoof algorithms that are not available in the training set. This study presents a method for voice spoof algorithms recognition based on incremental learning, taking into account the data flow scenarios where new spoof algorithms keep appearing in reality. Our experimental results on the LA dataset of ASVspoof2019 show that our system can improve the generalization of spoof detection and identify new voice spoof algorithms without catastrophic forgetting.