{"ID":5438593,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T01:40:09.565152011Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31074","arxiv_id":"2606.31074","title":"Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks","abstract":"Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics. In this study, we propose a novel Triospect Detection Framework by using additional perspectives of content (core ideas) and expression (stylistic elements) within a given text. Experiments on two benchmarks involving 17 attacks, 12 domains, and 17 source models demonstrate that Triospect is robust against these attacks. It improves the strong baseline by a significant margin of 22.3% (AUROC) and 13% (TPR01) on the Humanize-16K after-attack subset, and by 9.1% (AUROC) and 22% (TPR01) on the adversarial RAID. This framework marks a pioneering effort in statistical methods to enhance detection reliability against attacks. We release our data and code at https://github.com/baoguangsheng/triospect.","short_abstract":"Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics. In this study, we propose a novel Triospect Detection Framework by using additional perspectives of content (core ideas) and expression (stylistic elements) within a given text. Experiments on two benchmarks involvin...","url_abs":"https://arxiv.org/abs/2606.31074","url_pdf":"https://arxiv.org/pdf/2606.31074v1","authors":"[\"Guangsheng Bao\",\"Lihua Rong\",\"Yanbin Zhao\",\"Xiao Yu\",\"Qiji Zhou\",\"Yue Zhang\"]","published":"2026-06-30T03:02:42Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":613760,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-01T01:17:58.482524686Z","DeletedAt":null,"paper_id":5438593,"paper_url":"https://arxiv.org/abs/2606.31074","paper_title":"Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks","repo_url":"https://github.com/baoguangsheng/triospect","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}