{"ID":2922182,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T19:55:31.988541092Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.00872","arxiv_id":"2606.00872","title":"Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images","abstract":"AI-generated image detection is a moving-target problem: detectors trained on one generator often fail when a new generator appears, and only a few labeled examples are available. We study a simple image-to-table formulation for this regime, where each image is encoded by a frozen DINOv3 backbone, its CLS feature is reduced to a 500-dimensional structured row with PCA, and TabPFN performs real/fake classification by in-context tabular inference rather than task-specific classifier training. This turns fake-image detection into low-data structured prediction over learned visual features, making detector adaptation depend on the labeled context set instead of gradient-based fine-tuning. On GenImage, LATTE, a recent state-of-the-art detector, remains stronger when many labeled samples from all generators are available, by 7.4% in the largest pooled setting, but DINOv3-PCA-TabPFN is stronger in the practically important low-data regime, outperforming LATTE by up to 8.2%, and in transfer settings where the detector must generalize from one generator to another. These results position tabular foundation models as a strong complementary adaptation mechanism for image forensics, shifting adaptation from detector retraining to lightweight in-context updates with a small labeled set of examples. Code URL: https://github.com/jpwalter30/Towards-Generalizable-Detection-of-AI-Generated-Images","short_abstract":"AI-generated image detection is a moving-target problem: detectors trained on one generator often fail when a new generator appears, and only a few labeled examples are available. We study a simple image-to-table formulation for this regime, where each image is encoded by a frozen DINOv3 backbone, its CLS feature is re...","url_abs":"https://arxiv.org/abs/2606.00872","url_pdf":"https://arxiv.org/pdf/2606.00872v1","authors":"[\"Jan Philip Walter\",\"Shashank Agnihotri\",\"Margret Keuper\"]","published":"2026-05-30T20:00:25Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":612650,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T02:42:49.606572591Z","DeletedAt":null,"paper_id":2922182,"paper_url":"https://arxiv.org/abs/2606.00872","paper_title":"Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images","repo_url":"https://github.com/jpwalter30/Towards-Generalizable-Detection-of-AI-Generated-Images","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}