English
Related papers

Related papers: Differentially Private Language Models Benefit fro…

200 papers

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…

Machine Learning · Computer Science 2024-06-21 Zhiqi Bu , Yu-Xiang Wang , Sheng Zha , George Karypis

Differential Privacy (DP) for text matured from disjointed word-level substitutions to contiguous sentence-level rewriting by leveraging the generative capacity of language models. While this form of text privatization is best suited for…

Computation and Language · Computer Science 2026-04-30 Stefan Arnold

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…

Machine Learning · Computer Science 2019-03-05 H. Brendan McMahan , Galen Andrew , Ulfar Erlingsson , Steve Chien , Ilya Mironov , Nicolas Papernot , Peter Kairouz

Private and public organizations regularly collect and analyze digitalized data about their associates, volunteers, clients, etc. However, because most personal data are sensitive, there is a key challenge in designing privacy-preserving…

Cryptography and Security · Computer Science 2022-04-05 Héber H. Arcolezi

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.…

Machine Learning · Computer Science 2018-04-12 Yue Wang , Daniel Kifer , Jaewoo Lee

Differentially private stochastic gradient descent (DP-SGD) allows models to be trained in a privacy-preserving manner, but has proven difficult to scale to the era of foundation models. We introduce DP-ZO, a private fine-tuning framework…

Machine Learning · Computer Science 2025-02-03 Xinyu Tang , Ashwinee Panda , Milad Nasr , Saeed Mahloujifar , Prateek Mittal

Deep learning (DL) models for natural language processing (NLP) tasks often handle private data, demanding protection against breaches and disclosures. Data protection laws, such as the European Union's General Data Protection Regulation…

Computation and Language · Computer Science 2022-05-23 Samuel Sousa , Roman Kern

Large language models (LLMs) are primarily accessed via commercial APIs, but this often requires users to expose their data to service providers. In this paper, we explore how users can stay in control of their data by using privacy…

Computation and Language · Computer Science 2025-10-21 Guillem Ramírez , Alexandra Birch , Ivan Titov

Tuning the hyperparameters of differentially private (DP) machine learning (ML) algorithms often requires use of sensitive data and this may leak private information via hyperparameter values. Recently, Papernot and Steinke (2022) proposed…

Machine Learning · Computer Science 2024-02-14 Antti Koskela , Tejas Kulkarni

Applying differential privacy (DP) by means of the DP-SGD algorithm to protect individual data points during training is becoming increasingly popular in NLP. However, the choice of granularity at which DP is applied is often neglected. For…

Computation and Language · Computer Science 2024-09-27 Doan Nam Long Vu , Timour Igamberdiev , Ivan Habernal

Differential Privacy (DP) is the de facto standard for reasoning about the privacy guarantees of a training algorithm. Despite the empirical observation that DP reduces the vulnerability of models to existing membership inference (MI)…

Machine Learning · Computer Science 2022-12-20 Anvith Thudi , Ilia Shumailov , Franziska Boenisch , Nicolas Papernot

Machine learned models trained on organizational communication data, such as emails in an enterprise, carry unique risks of breaching confidentiality, even if the model is intended only for internal use. This work shows how confidentiality…

Cryptography and Security · Computer Science 2021-05-31 Masoumeh Shafieinejad , Huseyin Inan , Marcello Hasegawa , Robert Sim

The objective of machine learning is to extract useful information from data, while privacy is preserved by concealing information. Thus it seems hard to reconcile these competing interests. However, they frequently must be balanced when…

Machine Learning · Computer Science 2014-12-25 Zhanglong Ji , Zachary C. Lipton , Charles Elkan

We address the problem of learning a machine learning model from training data that originates at multiple data owners while providing formal privacy guarantees regarding the protection of each owner's data. Existing solutions based on…

Cryptography and Security · Computer Science 2025-03-12 Sikha Pentyala , Davis Railsback , Ricardo Maia , Rafael Dowsley , David Melanson , Anderson Nascimento , Martine De Cock

In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection. Concomitant with this rise in…

Machine Learning · Statistics 2019-06-04 Abhishek Bhowmick , John Duchi , Julien Freudiger , Gaurav Kapoor , Ryan Rogers

Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. As a result, such approaches often struggle with hyper-parameter tuning…

Machine Learning · Computer Science 2024-10-29 Kristjan Greenewald , Yuancheng Yu , Hao Wang , Kai Xu

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…

Cryptography and Security · Computer Science 2021-10-13 Jiaxiang Liu , Simon Oya , Florian Kerschbaum

The combination of deep neural networks and Differential Privacy has been of increasing interest in recent years, as it offers important data protection guarantees to the individuals of the training datasets used. However, using…

Machine Learning · Computer Science 2021-06-03 Osvald Frisk , Friedrich Dörmann , Christian Marius Lillelund , Christian Fischer Pedersen

Diferentially private (DP) synthetic datasets are a powerful approach for training machine learning models while respecting the privacy of individual data providers. The effect of DP on the fairness of the resulting trained models is not…

Machine Learning · Statistics 2021-06-21 Mayana Pereira , Meghana Kshirsagar , Sumit Mukherjee , Rahul Dodhia , Juan Lavista Ferres

Ensuring user privacy by synthesizing data from large language models (LLMs) tuned under differential privacy (DP) has become popular recently. However, the impact of DP fine-tuned LLMs on the quality of the language and the utility of the…

Computation and Language · Computer Science 2025-09-16 Erion Çano , Ivan Habernal