{"ID":6537501,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11538","arxiv_id":"2607.11538","title":"Evidence Subspace Projection: Measuring How Much Evidence Explains Deepfake Detection in Self-Supervised Speech Models","abstract":"Self-supervised learning (SSL) models are widely used as feature extractors for state-of-the-art audio deepfake detection, but it remains unclear how to directly and quantitatively connect what SSL models capture to detection decisions. To address this gap, we propose Evidence Subspace Projection, a method that represents both evidence factors (e.g., attack category, codec, gender, transmission) and authenticity labels in a shared space constructed from SSL models' neuron activation patterns. By projecting the decision vector onto each evidence subspace, we obtain a scalar ratio that quantifies the explanatory power of each evidence type. We evaluate SSL models in raw, fine-tuned, and post-trained settings on multiple datasets. The results confirm findings from established studies, validating the proposed method, and reveal new insights into model behavior.","short_abstract":"Self-supervised learning (SSL) models are widely used as feature extractors for state-of-the-art audio deepfake detection, but it remains unclear how to directly and quantitatively connect what SSL models capture to detection decisions. To address this gap, we propose Evidence Subspace Projection, a method that represe...","url_abs":"https://arxiv.org/abs/2607.11538","url_pdf":"https://arxiv.org/pdf/2607.11538v1","authors":"[\"Yixuan Xiao\",\"Cheng-Wei Lin\",\"Xin Wang\",\"Yassine El Kheir\",\"Arnab Das\",\"Tim Polzehl\",\"Sebastian Möller\",\"Ngoc Thang Vu\"]","published":"2026-07-13T13:22:19Z","proceeding":"cs.SD","tasks":"[\"cs.SD\"]","methods":"[]","has_code":false}