Deepfakes as a threat to a speaker and facial recognition: An overview of tools and attack vectors

A Firc, K Malinka, P Hanáček - Heliyon, 2023 - cell.com
Deepfakes present an emerging threat in cyberspace. Recent developments in machine
learning make deepfakes highly believable, and very difficult to differentiate between what is …

Deepfake Speech Recognition and Detection

HC Chang - International Journal of Pattern Recognition and …, 2023 - World Scientific
Deepfake technology, especially deep voice, which has been derived from artificial
intelligence in recent years, is potentially harmful, and the public is not yet wary. However …

[PDF][PDF] Differential-based Deepfake Speech Detection

BV STANĚK - theses.cz
Deepfake speech technology, which can create highly realistic fake audio, poses significant
challenges, from enabling multi-million dollar scams to complicating legal evidence's …

Inconspicuous Audio Anonymization: A Real-Time Approach with a Neural Network Model

A Amjad, HT Chang - Available at SSRN 4962902 - papers.ssrn.com
Abstract Automatic Speaker Recognition (ASR) systems present an increasingly significant
risk to the privacy of individuals by facilitating the unwitting identification and possible …