In the privacy-utility tradeoff of a model trained on benchmark language and vision tasks,
remarkable improvements have been widely reported when the model is pretrained on …

Per-example gradient clipping is a key algorithmic step that enables practical differential
private (DP) training for deep learning models. The choice of clipping threshold $ R …

As the deployment of pre-trained language models (PLMs) expands, pressing security
concerns have arisen regarding the potential for malicious extraction of training data, posing …

Differentially private learning algorithms inject noise into the learning process. While the
most common private learning algorithm, DP-SGD, adds independent Gaussian noise in …

In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-
SGD) performs worse than SGD due to per-sample gradient clipping and noise addition. A …

In-context learning (ICL) is an important capability of Large Language Models (LLMs),
enabling these models to dynamically adapt based on specific, in-context exemplars …

Generating differentially private (DP) synthetic data that closely resembles the original
private data is a scalable way to mitigate privacy concerns in the current data-driven world …

Fine-tuning large pretrained models on private datasets may run the risk of violating privacy.
Differential privacy is a framework for mitigating privacy risks by enforcing algorithmic …

Privacy-preserving machine learning aims to train models on private data without leaking
sensitive information. Differential privacy (DP) is considered the gold standard framework for …

We propose a new family of label randomizers for training regression models under the
constraint of label differential privacy (DP). In particular, we leverage the trade-offs between …