đ§”3/3:
2) âGeneralizable speech deepfake detection via meta-learned LoRAâ by Laakkonen, Kukanov, HautamĂ€ki arxiv.org/abs/2502.108...
Speech deepfake detection under attack shift: LoRA adapters + meta-learning (MLDG) to learn transferable cues rather than overfitting to specific spoofing methods.
Reliable detection of speech deepfakes (spoofs) must remain effective when the distribution of spoofing attacks shifts. We frame the task as domain generalization and show that inserting Low-Rank Adap...
