{"ID":2896360,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.06470","arxiv_id":"2507.06470","title":"Open-Set Source Tracing of Audio Deepfake Systems","abstract":"Existing research on source tracing of audio deepfake systems has focused primarily on the closed-set scenario, while studies that evaluate open-set performance are limited to a small number of unseen systems. Due to the large number of emerging audio deepfake systems, robust open-set source tracing is critical. We leverage the protocol of the Interspeech 2025 special session on source tracing to evaluate methods for improving open-set source tracing performance. We introduce a novel adaptation to the energy score for out-of-distribution (OOD) detection, softmax energy (SME). We find that replacing the typical temperature-scaled energy score with SME provides a relative average improvement of 31% in the standard FPR95 (false positive rate at true positive rate of 95%) measure. We further explore SME-guided training as well as copy synthesis, codec, and reverberation augmentations, yielding an FPR95 of 8.3%.","short_abstract":"Existing research on source tracing of audio deepfake systems has focused primarily on the closed-set scenario, while studies that evaluate open-set performance are limited to a small number of unseen systems. Due to the large number of emerging audio deepfake systems, robust open-set source tracing is critical. We lev...","url_abs":"https://arxiv.org/abs/2507.06470","url_pdf":"https://arxiv.org/pdf/2507.06470v1","authors":"[\"Nicholas Klein\",\"Hemlata Tak\",\"Elie Khoury\"]","published":"2025-07-09T01:03:36Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[]","has_code":false}