Can I read Generalizable speech deepfake detection via meta-learned LoRA on EtoBox?

Generalizable speech deepfake detection via meta-learned LoRA by Laakkonen, Janne; Kukanov, Ivan; Hautamäki, Ville is a scholarly article available to read on EtoBox.

What is Generalizable speech deepfake detection via meta-learned LoRA about?

Generalizable deepfake detection can be formulated as a detection problem where labels (bonafide and fake) are fixed but distributional drift affects the deepfake set. We can always train our detector with one-selected attacks and bonafide data, but an attacker can generate new attacks by just retraining his generator with a different seed. One reasonable approach is to simply pool all different attack types available in training time. Our proposed approach is to utilize meta-learning in combination with LoRA adapters to learn the structure in the training data that is common to all attack types.

Author

Laakkonen, Janne; Kukanov, Ivan; Hautamäki, Ville

Published

2025

Language

EN