Detection-Guided Adaptive Purification with Diffusion Models for Robust Audio Deepfake Detection

arXiv:2610.10752v1 Announce Type: new Abstract: Audio deepfake detectors remain vulnerable to adversarial perturbations that suppress the acoustic cues used for detection, allowing manipulated utterances to evade the detector. Although existing defenses can improve robustness, they require retraining the detector or introduce additional distortion.

Read the full article at arXiv cs.CR →