Audio DeepFakes
Audio deepfakes, realistic synthetic audio recordings created using AI, pose significant threats to security and trust. Current research focuses on developing robust detection methods, often employing transformer-based architectures and contrastive learning techniques to improve accuracy and resistance to manipulation attacks, as well as exploring source tracing to identify the generation methods used. This field is crucial due to the increasing prevalence of audio deepfakes in misinformation campaigns and other malicious activities, driving the need for effective detection and attribution strategies.
Papers
November 29, 2024
November 21, 2024
October 9, 2024
September 9, 2024
July 10, 2024
April 24, 2024
April 22, 2024
January 17, 2024
November 29, 2023
November 6, 2023
October 5, 2023
December 30, 2022
November 1, 2022
October 12, 2022
June 27, 2022
March 28, 2022
December 6, 2021