Related papers: Large Language Models Can Be Strong Differentially…
We introduce new differentially private (DP) mechanisms for gradient-based machine learning (ML) with multiple passes (epochs) over a dataset, substantially improving the achievable privacy-utility-computation tradeoffs. We formalize the…
Recent developments have underscored the critical role of \textit{differential privacy} (DP) in safeguarding individual data for training machine learning models. However, integrating DP oftentimes incurs significant model performance…
Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…
Temporal difference (TD) learning is a widely used method to evaluate policies in reinforcement learning. While many TD learning methods have been developed in recent years, little attention has been paid to preserving privacy and most of…
In this paper, an adjustment to the original differentially private stochastic gradient descent (DPSGD) algorithm for deep learning models is proposed. As a matter of motivation, to date, almost no state-of-the-art machine learning…
Differentially Private Stochastic Gradient Descent (DP-SGD) has become a widely used technique for safeguarding sensitive information in deep learning applications. Unfortunately, DPSGD's per-sample gradient clipping and uniform noise…
We study (differentially) private federated learning (FL) of language models. The language models in cross-device FL are relatively small, which can be trained with meaningful formal user-level differential privacy (DP) guarantees when…
Differentially private (DP) synthetic data generation plays a pivotal role in developing large language models (LLMs) on private data, where data owners cannot provide eyes-on access to individual examples. Generating DP synthetic data…
Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding…
Differential privacy (DP) provides a formal privacy guarantee that prevents adversaries with access to machine learning models from extracting information about individual training points. Differentially private stochastic gradient descent…
The Transformer has emerged as a versatile and effective architecture with broad applications. However, it still remains an open problem how to efficiently train a Transformer model of high utility with differential privacy guarantees. In…
Machine learning models trained with differentially-private (DP) algorithms such as DP-SGD enjoy resilience against a wide range of privacy attacks. Although it is possible to derive bounds for some attacks based solely on an…
Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (DP) has emerged as a principled framework that limits the influence of individual data…
Large Language models (LLMs) are achieving state-of-the-art performance in many different downstream tasks. However, the increasing urgency of data privacy puts pressure on practitioners to train LLMs with Differential Privacy (DP) on…
Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…
This paper studies how to learn variational autoencoders with a variety of divergences under differential privacy constraints. We often build a VAE with an appropriate prior distribution to describe the desired properties of the learned…
Large Language Models (LLMs) have emerged as dominant tools for various tasks, particularly when tailored for a specific target by prompt tuning. Nevertheless, concerns surrounding data privacy present obstacles due to the tuned prompts'…
Differentially private stochastic gradient descent (DP-SGD) is the canonical approach to private deep learning. While the current privacy analysis of DP-SGD is known to be tight in some settings, several empirical results suggest that…
Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained language model on limited target datasets is often plagued by…
Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information. To provide formal and rigorous privacy guarantee, many learning systems now incorporate…