{"type":"ScholarlyArticle","title":"Breaking the Trade-off: Orthogonal Semantic Decoupling for Generalizable and Fair Deepfake Detection","authors":[{"name":"Zhongyu Shi","slug":"zhongyu-shi","given":"Zhongyu","family":"Shi","affiliation":""},{"name":"Siyu Peng","slug":"siyu-peng","given":"Siyu","family":"Peng","affiliation":""},{"name":"Yimin Kang","slug":"yimin-kang","given":"Yimin","family":"Kang","affiliation":""},{"name":"Ruiyang Xia","slug":"ruiyang-xia","given":"Ruiyang","family":"Xia","affiliation":""},{"name":"Yizhi Fang","slug":"yizhi-fang","given":"Yizhi","family":"Fang","affiliation":""},{"name":"Weiping Wen","slug":"weiping-wen","given":"Weiping","family":"Wen","affiliation":""},{"name":"Zeyu Gu","slug":"zeyu-gu","given":"Zeyu","family":"Gu","affiliation":""},{"name":"Sai Cheng","slug":"sai-cheng","given":"Sai","family":"Cheng","affiliation":""}],"abstract":"Deepfake detection faces dual challenges in real-world deployment: cross-domain generalization and demographic fairness. Existing approaches often struggle with a trade-off between these goals. Generalization-oriented detectors can over-rely on demographic shortcuts, while fairness constraints tend to steer optimization away from the most discriminative decision boundary. To address this, we propose Orthogonal Semantic Decoupling (OSD), a framework that decouples demographic semantics from forgery cues. Specifically, we perform Singular Value Decomposition on the pretrained weights of a vision-language model, freezing the principal semantic subspace while learning parameter-efficient low-rank experts in the residual subspace. The experts comprise (1) Demographic Semantic Experts, a set of experts specialized via hard sampling and routed based on the similarities between image embeddings and text embeddings of predefined descriptions; and (2) a Universal Forgery Expert, which captures forgery features transferable across domains and demographics. Extensive experiments across multiple benchmarks demonstrate that our approach outperforms state-of-the-art methods in both generalization and fairness, breaking the trade-off. The code is available at https://github.com/sonder-lin/osd-deepfake-detection.","doi":"10.24963/ijcai.2026/84","url":"https://ijcai.org/proceedings/2026/84","pdf":"https://ijcai.org/proceedings/2026/0084.pdf","markdown":"https://ijcai.org/proceedings/2026/84.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/84","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI Ethics, Trust, Fairnes","track":"Main Track","number":84,"pages":{"first":744,"last":752},"keywords":["AI Ethics, Trust, Fairnes: Safety and robustness","AI Ethics, Trust, Fairnes: Fairness and diversity","AI Ethics, Trust, Fairnes: Bias"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}