1. Deep Learning with Differential Privacy
2. Privacy Preserving Text Representation Learning
3. Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al. 2021. Extracting training data from large language models. In 30th USENIX Security Symposium (USENIX Security 21). 2633--2650. https://www.usenix.org/conference/usenixsecurity21/presentation/carlini-extracting
4. TEM: High Utility Metric Differential Privacy on Text