相关论文: Selective Pre-training for Private Fine-tuning

In this work we address the practical challenges of training machine learning models on privacy-sensitive datasets by introducing a modular approach that minimizes changes to training algorithms, provides a variety of configuration…

This position paper investigates the integration of Differential Privacy (DP) in the training of Mixture of Experts (MoE) models within the field of natural language processing. As Large Language Models (LLMs) scale to billions of…

In machine learning, privacy requirements at inference or deployment time often evolve due to changing policies, regulations, or user preferences. In this work, we aim to construct a magnitude of models to satisfy any target differential…

The process of data mining with differential privacy produces results that are affected by two types of noise: sampling noise due to data collection and privacy noise that is designed to prevent the reconstruction of sensitive information.…

We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a recent privacy-preserving approach suitable for solving downstream tasks with sensitive data. Existing work has demonstrated that high accuracy…

Fine-tuning is a prominent technique to adapt a pre-trained language model to downstream scenarios. In parameter-efficient fine-tuning, only a small subset of modules are trained over the downstream datasets, while leaving the rest of the…

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…

Large language models are classically trained in stages: pretraining on raw text followed by post-training for instruction following and reasoning. However, this separation creates a fundamental limitation: many desirable behaviors such as…

We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples contributed by each user. We study two variants of DP-SGD…

Differential privacy (DP) is a privacy-preserving paradigm that protects the training data when training deep learning models. Critically, the performance of models is determined by the training hyperparameters, especially those of the…

Privacy preserving deep learning is an emerging field in machine learning that aims to mitigate the privacy risks in the use of deep neural networks. One such risk is training data extraction from language models that have been trained on…

For machine learning with tabular data, Table Transformer (TabTransformer) is a state-of-the-art neural network model, while Differential Privacy (DP) is an essential component to ensure data privacy. In this paper, we explore the benefits…

To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the…

For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclear to what extent…

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

Recent research has shown that smaller language models can acquire substantial reasoning abilities when fine-tuned with reasoning exemplars crafted by a significantly larger teacher model. We explore this paradigm for the financial domain,…

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…

Despite their impressive success, training foundation models remains computationally costly. This paper investigates how to efficiently train speech foundation models with self-supervised learning (SSL) under a limited compute budget. We…

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…

A key promise of machine learning is the ability to assist users with personal tasks. Because the personal context required to make accurate predictions is often sensitive, we require systems that protect privacy. A gold standard…