@misc{li2024digger, title={Digger: Detecting Copyright Content Mis-usage in Large Language Model Training}, author={Haodong Li and Gelei Deng and Yi Liu and Kailong Wang and Yuekang Li and Tianwei Zhang and Yang Liu and Guoai Xu and Guosheng Xu and Haoyu Wang}, year={2024}, eprint={2401.00676}, archivePrefix={arXiv}, primaryClass={cs.CR}, url={https://arxiv.org/abs/2401.00676} }