{"paper":{"title":"Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"High-level semantics act as a structural prior to reconstruct a unified yet discriminative artifact feature space, enabling a practical monolithic model for fake image detection.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, Chaogun Niu, Chenfan Qu, Jian Liu, Jingjing Liu, Ji-Zhe Zhou, Mingqi Fang, Xiaochen Ma, Xuekang Zhu, Zhenming Wang, Zhe Yang","submitted_at":"2026-02-06T13:03:26Z","abstract_excerpt":"Fake Image Detection (FID), aiming at unified detection across four image forensic subdomains, is critical in real-world forensic scenarios. Compared with ensemble approaches, monolithic FID models are theoretically more promising, but to date, consistently yield inferior performance in practice. In this work, we identify the intrinsic distinctness of artifacts across subdomains, a critical barrier we term the ``Ji-Zhe phenomenon\". Driven by this phenomenon, we diagnose the cause of this underperformance for the first time: the collapse of the artifact feature space. The core challenge for dev"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SICA outperforms 15 state-of-the-art methods and reconstructs the target unified-yet-discriminative artifact feature space in a near-orthogonal manner, thus firmly validating our hypothesis.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"High-level semantics can serve as a structural prior for the reconstruction of the artifact feature space.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SICA uses semantic-induced constrained adaptation to build the first monolithic fake image detector that reconstructs a unified-yet-discriminative artifact feature space and outperforms 15 prior methods on a new dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"High-level semantics act as a structural prior to reconstruct a unified yet discriminative artifact feature space, enabling a practical monolithic model for fake image detection.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5131da68a2b4818b799805abe649ccfe430aecf976dfd90dd507e25f8d101933"},"source":{"id":"2602.06676","kind":"arxiv","version":4},"verdict":{"id":"0656d4d0-3eee-44ae-95bc-3aab8bdf89fe","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:53:37.743500Z","strongest_claim":"SICA outperforms 15 state-of-the-art methods and reconstructs the target unified-yet-discriminative artifact feature space in a near-orthogonal manner, thus firmly validating our hypothesis.","one_line_summary":"SICA uses semantic-induced constrained adaptation to build the first monolithic fake image detector that reconstructs a unified-yet-discriminative artifact feature space and outperforms 15 prior methods on a new dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"High-level semantics can serve as a structural prior for the reconstruction of the artifact feature space.","pith_extraction_headline":"High-level semantics act as a structural prior to reconstruct a unified yet discriminative artifact feature space, enabling a practical monolithic model for fake image detection."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.06676/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":2,"snapshot_sha256":"1f39a08a06bd520adaf792cd57e30c6a75f7c73c9076587352ddd6a1e5054214"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}