arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.09200cs.LG
收藏

生成文本检测基准中的污染问题

Sure! Here's a short and concise title for your paper: "Contamination in Generated Text Detection Benchmarks"

IT Security Infrastructures Lab, FAU Erlangen-Nürnberg(FAU埃尔兰根-纽伦堡大学信息安全部署实验室)

Philipp Dingfelder, Christian Riess

AI总结:

针对生成文本检测基准存在数据质量问题(如DetectRL含98.5%简单AI生成模式易被检测器当作捷径导致易受欺骗攻击),提出多清洗操作处理数据集,实验证明可提升抗攻击能力并公开数据集。

摘要:

大型语言模型在众多应用中的使用日益广泛。为防止非法使用,能够检测AI生成的文本是可取的。此类检测器的训练和评估严重依赖合适的基准数据集。多个团队承担了为该任务收集、整理和发布大型多样化数据集的繁琐工作。然而,确保此类数据集所有相关方面的高质量仍是一项未解决的挑战。例如,DetectRL基准在98.5%的Claude-LLM数据中表现出相对简单的AI生成模式。这些模式可能包括“Sure! Here is the academic article abstract:”等介绍性词语,或LLM拒绝提示任务的情况。在这项工作中,我们证明在这类数据上训练的检测器会将这些模式用作捷径,这为针对训练后检测器的欺骗攻击提供了便利。因此,我们通过多种清洗操作对DetectRL数据集进行了重新处理。实验表明,这种数据清洗使直接攻击变得更加困难。重新处理后的数据集已公开可用。

英文摘要:

Large language models are increasingly used for many applications. To prevent illicit use, it is desirable to be able to detect AI-generated text. Training and evaluation of such detectors critically depend on suitable benchmark datasets. Several groups took on the tedious work of collecting, curating, and publishing large and diverse datasets for this task. However, it remains an open challenge to ensure high quality in all relevant aspects of such a dataset. For example, the DetectRL benchmark exhibits relatively simple patterns of AI-generation in 98.5% of the Claude-LLM data. These patterns may include introductory words such as "Sure! Here is the academic article abstract:", or instances where the LLM rejects the prompted task. In this work, we demonstrate that detectors trained on such data use such patterns as shortcuts, which facilitates spoofing attacks on the trained detectors. We consequently reprocessed the DetectRL dataset with several cleansing operations. Experiments show that such data cleansing makes direct attacks more difficult. The reprocessed dataset is publicly available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑