{"type":"ScholarlyArticle","title":"PURE: Purging Unrelated Representations for Content-Agnostic Forgery Detection","authors":[{"name":"Xinyu Wu","slug":"xinyu-wu","given":"Xinyu","family":"Wu","affiliation":""},{"name":"Dong Li","slug":"dong-li","given":"Dong","family":"Li","affiliation":""},{"name":"Minglai Shao","slug":"minglai-shao","given":"Minglai","family":"Shao","affiliation":""},{"name":"Xintao Wu","slug":"xintao-wu","given":"Xintao","family":"Wu","affiliation":""},{"name":"Zhong Chen","slug":"zhong-chen","given":"Zhong","family":"Chen","affiliation":""},{"name":"Chen Zhao","slug":"chen-zhao","given":"Chen","family":"Zhao","affiliation":""}],"abstract":"Existing AI-generated image (AIGI) detectors perform well in-domain but degrade severely under distribution shift. We observe that this failure is mainly caused by content shortcuts, where detectors spuriously couple forgery artifacts with semantic content, such as object categories or demographic attributes, learning content–label correlations instead of generalizable forgery patterns. To address this issue, we propose PURE (Purging Unrelated Representations for Content-Agnostic Forgery Detection), which achieves content-agnostic detection through two complementary components: a Causal Semantic Generative (CSG) mechanism that disentangles semantic representations from forgery-irrelevant nuisance factors, and a Gaussian Mixture Model (GMM)-based prototype alignment module that suppresses category-specific content bias. Extensive experiments on CIFAKE, GenImage, and AlFace show that PURE achieves superior generalization under spurious correlation reversal. The code is available at https://github.com/wuxinyu519/PURE.","doi":"10.24963/ijcai.2026/207","url":"https://ijcai.org/proceedings/2026/207","pdf":"https://ijcai.org/proceedings/2026/0207.pdf","markdown":"https://ijcai.org/proceedings/2026/207.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/207","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":"Computer Vision","track":"Main Track","number":207,"pages":{"first":1857,"last":1865},"keywords":["Computer Vision: Machine learning for vision","Computer Vision: Multimodal learning","Computer Vision: Representation learning","Machine Learning: Causality","Machine Learning: Classification"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}