[2603.26856] AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection

Computer Science > Sound arXiv:2603.26856 (cs) [Submitted on 27 Mar 2026] Title:AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection Authors:Hai-Son Nguyen-Le, Hung-Cuong Nguyen-Thanh, Nhien-An Le-Khac, Dinh-Thuc Nguyen, Hong-Hanh Nguyen-Le View a PDF of the paper titled AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection, by Hai-Son Nguyen-Le and 4 other authors View PDF HTML (experimental) Abstract:The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors suffer from a critical bias problem, leading to poor generalization across unseen datasets. This paper proposes Artifact-Focused Self-Synthesis (AFSS), a method designed to mitigate this bias by generating pseudo-fake samples from real audio via two mechanisms: self-conversion and self-reconstruction. The core insight of AFSS lies in enforcing same-speaker constraints, ensuring that real and pseudo-fake samples share identical speaker identity and semantic content. This forces the detector to focus exclusively on generation artifacts rather than irrelevant confounding factors. Furthermore, we introduce a learnable reweighting loss to dynamically emphasize synthetic samples during training. Extensive experiments across 7 datasets demonstrate that AFSS achieves state-of-the-art performance with an average EER of 5.45\%, including a significant reduction to 1.23\% on WaveFake and 2.70\% on In-the-Wild, al...