arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.01152cs.CLcs.AI
收藏

AI生成文本取证系统综述:检测、归因与特征刻画

A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization

Arizona State University(亚利桑那州立大学);Stanford University(斯坦福大学);Amazon GenAI(亚马逊生成式人工智能部门)

Tharindu Kumarage, Garima Agrawal, Paras Sheth, Raha Moraffah, Aman Chadha, Joshua Garland, Huan Liu

AI总结:

本文综述AI生成文本取证系统,围绕检测、归因与特征刻画构建分类体系,梳理现有研究与资源,并讨论该领域挑战及未来方向。

摘要:

近来,我们见证了能够生成高质量文本的先进大语言模型(LLM)的迅速普及。尽管这些LLM已经革新了多个领域的文本生成,但它们也给信息生态系统带来了重大风险,例如有可能大规模生成具有说服力的宣传内容、错误信息和虚假信息。本文对AI生成文本取证系统进行了综述,这是一个应对LLM滥用挑战的新兴领域。我们通过引入详细的分类体系,概述了AI生成文本取证方面的现有工作,并聚焦三大核心支柱:检测、归因和特征刻画。这些支柱使人们能够切实理解AI生成文本:识别AI生成内容(检测)、确定所涉及的具体AI模型(归因),以及对文本的潜在意图进行分组(特征刻画)。此外,我们还探讨了AI生成文本取证研究的可用资源,并讨论了AI时代取证系统不断演变的挑战和未来方向。

英文摘要:

We have witnessed lately a rapid proliferation of advanced Large Language Models (LLMs) capable of generating high-quality text. While these LLMs have revolutionized text generation across various domains, they also pose significant risks to the information ecosystem, such as the potential for generating convincing propaganda, misinformation, and disinformation at scale. This paper offers a review of AI-generated text forensic systems, an emerging field addressing the challenges of LLM misuses. We present an overview of the existing efforts in AI-generated text forensics by introducing a detailed taxonomy, focusing on three primary pillars: detection, attribution, and characterization. These pillars enable a practical understanding of AI-generated text, from identifying AI-generated content (detection), determining the specific AI model involved (attribution), and grouping the underlying intents of the text (characterization). Furthermore, we explore available resources for AI-generated text forensics research and discuss the evolving challenges and future directions of forensic systems in an AI era.

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。

↑