Lukas Wutschitz

Training Data Leakage Analysis in Language Models

2021 · arXiv (Cornell University)

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with the …

Differentially Private Fine-tuning of Language Models

2024 · Journal of Privacy and Confidentiality

We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus utility tradeoffs on many standard NLP tasks. We propose a meta-framework for this …