[1]
Wu, H. et al. 2025. DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately. Proceedings of the AAAI Conference on Artificial Intelligence. 39, 26 (Apr. 2025), 27706–27714. DOI:https://doi.org/10.1609/aaai.v39i26.34985.