← 研踪 PaperTrailarXiv:2611.20158 · v1
Who Can You Hide Behind? Author-Conditioned Style Transfer and the Evasion of a Commercial AI-Text Detector
首次提交 2026-11-16 01:59
版本更新 2026-11-16 01:59
雷达观测 2026-11-17 12:06
摘要
AI-text detectors can be sensitive to changes in writing style. We examined this sensitivity by rewriting 991 AI-generated answers with Gemini, using prompts that included a writing sample from one of 55 named authors. We scored each original and its rewrite with the QuillBot AI detector. The median score fell from 100% to 0%, and the mean fell from 67.9% to 11.2%. Of the rewrites, 66% received a score of exactly 0%. Among the 699 originals scored at least 50%, 71% of rewrites scored below 10% (paired Wilcoxon signed-rank test, p-value below 1e-100). Scores varied across the authors used in the prompts. All rewrites associated with 10 authors scored 0%, whereas the mean score remained above 50% for six authors (Kruskal-Wallis test, p-value below 1e-80). Greater reuse of five-word sequences from the author sample was associated with lower scores, although rewrites with less than 5% reuse still averaged 15.2%. These results describe one detector and one rewriting system, not detectors in general. The study lacks a generic-rewrite baseline, did not measure preservation of meaning, and produced rewrites that were substantially longer than the originals.
作者备注:6 pages, 5 figures, 4 tables, Preprint
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-16 01:59 · 最新观测版本
Who Can You Hide Behind? Author-Conditioned Style Transfer and the Evasion of a Commercial AI-Text Detector
AI-text detectors can be sensitive to changes in writing style. We examined this sensitivity by rewriting 991 AI-generated answers with Gemini, using prompts that included a writing sample from one of 55 named authors. We scored each original and its rewrite with the QuillBot AI detector. The median score fell from 100% to 0%, and the mean fell from 67.9% to 11.2%. Of the rewrites, 66% received a score of exactly 0%. Among the 699 originals scored at least 50%, 71% of rewrites scored below 10% (paired Wilcoxon signed-rank test, p-value below 1e-100). Scores varied across the authors used in the prompts. All rewrites associated with 10 authors scored 0%, whereas the mean score remained above 50% for six authors (Kruskal-Wallis test, p-value below 1e-80). Greater reuse of five-word sequences from the author sample was associated with lower scores, although rewrites with less than 5% reuse still averaged 15.2%. These results describe one detector and one rewriting system, not detectors in general. The study lacks a generic-rewrite baseline, did not measure preservation of meaning, and produced rewrites that were substantially longer than the originals.
查看此版本解读 →查看此版本原文 ↗