基于信息同位素识别 AI 生成内容中的未授权训练数据
摘要
在规模化规律下，众多 AI 机构正加大构建高级 AI 模型的力度，积极收集高质量人类数据。然而，部分机构可能在为追求竞争优势时，无意或有意包含未经授权的数据（如涉及隐私或知识产权的敏感内容）用于训练，从而侵犯数据拥有者的权利。 compounded by the fact that these advanced AI services are typically built on opaque cloud platforms, which restricts access to internal information during AI training and inference, leaving only the generated outputs available for forensics. Thus, despite the introduction of legal frameworks by various countries to safeguard data rights, uncovering evidence of data misuse in modern opaque AI applications remains a significant challenge. In this paper, inspired by the ability of isotopes to trace elements within chemical reactions, we introduce the concept of information isotopes and elucidate their properties in tracing training data within opaque AI systems. Furthermore, we propose an information isotope tracing method designed to identify and provide evidence of unauthorized data usage by detecting the presence of target information isotopes in AI generations. We conduct experiments on ten AI models (including GPT-4o, Claude-3.5, and DeepSeek) and four benchmark datasets in critical domains (medical data, copyrighted books, and news). Results show that our method can distinguish training datasets from non-training datasets with 99% accuracy and significant evidence (p-value < 0.001) by examining a data entry equivalent in length to a research paper. The findings show the potential of our work as an inclusive tool for empowering individuals, including those without expertise in AI, to safeguard their data rights in the rapidly evolving era of AI advancements and applications.
引用
@article{arxiv.2503.20800,
title = {Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes},
author = {Qi Tao and Yin Jinhua and Cai Dongqi and Xie Yueqi and Wang Huili and Hu Zhiyang and Yang Peiru and Nan Guoshun and Zhou Zhili and Wang Shangguang and Lyu Lingjuan and Huang Yongfeng and Lane Nicholas},
journal= {arXiv preprint arXiv:2503.20800},
year = {2025}
}