{"paper":{"title":"Revisiting Simple Baselines for In-The-Wild Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin So-Tang, Kshitij Gurung, Orlando Castaneda","submitted_at":"2025-09-04T12:23:59Z","abstract_excerpt":"The widespread adoption of synthetic media demands accessible deepfake detectors and realistic benchmarks. While most existing research evaluates deepfake detectors on highly controlled datasets, we focus on the recently released \"in-the-wild\" benchmark, Deepfake-Eval-2024. Initial reporting on Deepfake-Eval-2024 showed that three finetuned open-source models achieve accuracies between 61% and 69%, significantly lagging behind the leading commercial deepfake detector with 82% accuracy. Our work revisits one of these baseline approaches, originally introduced by Ojha et al., which adapts standa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04150","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.04150/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}