{"ID":5935827,"CreatedAt":"2026-07-07T01:22:02.77346169Z","UpdatedAt":"2026-07-07T02:10:06.972658124Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03150","arxiv_id":"2607.03150","title":"An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures","abstract":"While deepfake audio detection systems achieve high performance in controlled benchmarks, their reliability often diminishes in the wild. Prior work shows that dataset-specific artifacts contribute to this gap. Yet, systematic tools to identify which acoustic properties a model exploits as shortcuts remain limited. We propose an intervention-based diagnostic framework, grounded in a directed graphical model, that formally distinguishes confound-driven shortcut dependencies from legitimate domain shift. We operationalise this through controlled acoustic perturbations targeting non-speech structure, spectral content, and signal energy, complemented by corpus-level distributional analysis. Evaluating XLS-R-300M with RawGAT-ST across ASVspoof challenges datasets, we quantify model sensitivity to specific intervention types. Results reveal that non-speech interventions produce the largest performance shifts, confirming non-speech intervals as a dominant shortcut.","short_abstract":"While deepfake audio detection systems achieve high performance in controlled benchmarks, their reliability often diminishes in the wild. Prior work shows that dataset-specific artifacts contribute to this gap. Yet, systematic tools to identify which acoustic properties a model exploits as shortcuts remain limited. We...","url_abs":"https://arxiv.org/abs/2607.03150","url_pdf":"https://arxiv.org/pdf/2607.03150v1","authors":"[\"Santiago Rubio\",\"Pilar Bello\",\"Dayana Ribas\",\"Antonio Miguel\",\"Eduardo Lleida\",\"Alfonso Ortega\"]","published":"2026-07-03T09:42:31Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.LG\"]","methods":"[]","has_code":false}