Researchers from CSIRO, Federation University Australia and RMIT University have developed a method to improve the detection of audio deepfakes. The use of audio deepfakes to impersonate voices is rising. The detection of audio deepfakes is becoming increasingly important.
Many cybercriminals no longer try to hack computer systems. It is far easier for them to hack people. Criminals are using deepfakes to bypass human controls to people to hand over confidential information.
Deepfake detection remains an important area of research for CSIRO. The agency recently revealed that many deepfake detection tools are ineffective.
RAISing the bar
The technique developed by the researchers is called Rehearsal with Auxiliary-Informed Sampling (RAIS). It determines whether an audio clip is real or artificially generated (a ‘deepfake’) and maintains performance over time as attack types evolve.
Earlier this year, an AI-cloned voice of the Italian Defence Minister requested a €1M ‘ransom’ from prominent business leaders with some convinced to pay. This is just one of many examples, highlighting the need for audio deepfake detectors.
Dr Kristen Moore from CSIRO’s Data61 says “RAIS solves this by automatically selecting and storing a small, but diverse set of past examples, including hidden audio traits that humans may not even notice, to help the AI learn the new deepfake styles without forgetting the old ones.”
RAIS uses a smart selection process powered by a network that generates ‘auxiliary labels’ for each audio sample. These labels help identify a diverse and representative set of audio samples to retain and rehearse. By incorporating extra labels beyond simple ‘fake’ or ‘real’ tags, RAIS ensures a richer mix of training data, improving its ability to remember and adapt over time.
The researchers say RAIS outperforms other deepfake detection methods with a 1,95% error rating across a sequence of five experiences. It remains effective with a small memory buffer and is designed to maintain accuracy as attacks become more sophisticated.
The software code to use RAIS is available on GitHub.
“Audio deepfakes are evolving rapidly, and traditional detection methods can’t keep up,” said Falih Gozi Febrinanto, a recent PhD graduate of Federation University Australia. “RAIS helps the model retain what it has learned and adapt to new attacks. Overall, it reduces the risk of forgetting and enhances its ability to detect deepfakes.”
Anthony is the founder of Australian Apple News. He is a long-time Apple user and former editor of Australian Macworld. He has contributed to many technology magazines and newspapers as well as appearing regularly on radio and occasionally on TV.