English
Related papers

Related papers: Differentially Private Language Models for Secure …

200 papers

Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects. However the majority of prior work has focused on scenarios where a single party owns all the data. In…

Cryptography and Security · Computer Science 2022-06-22 Ruihan Wu , Xin Yang , Yuanshun Yao , Jiankai Sun , Tianyi Liu , Kilian Q. Weinberger , Chong Wang

Deep learning models leak significant amounts of information about their training datasets. Previous work has investigated training models with differential privacy (DP) guarantees through adding DP noise to the gradients. However, such…

Machine Learning · Computer Science 2020-07-23 Milad Nasr , Reza Shokri , Amir houmansadr

Differential Privacy (DP) has been tailored to address the unique challenges of text-to-text privatization. However, text-to-text privatization is known for degrading the performance of language models when trained on perturbed text.…

Computation and Language · Computer Science 2023-10-18 Stefan Arnold , Nils Kemmerzell , Annika Schreiner

Pre-training on public data is an effective method to improve the performance for federated learning (FL) with differential privacy (DP). This paper investigates how large language models (LLMs) trained on public data can improve the…

Machine Learning · Computer Science 2024-08-08 Shanshan Wu , Zheng Xu , Yanxiang Zhang , Yuanbo Zhang , Daniel Ramage

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…

Machine Learning · Computer Science 2026-05-21 Qichuan Yin , Manzil Zaheer , Tian Li

Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…

Computation and Language · Computer Science 2024-07-01 Pedro Faustini , Shakila Mahjabin Tonni , Annabelle McIver , Qiongkai Xu , Mark Dras

As large language models (LLMs) increasingly underpin technological advancements, the privacy of their training data emerges as a critical concern. Differential Privacy (DP) serves as a rigorous mechanism to protect this data, yet its…

Machine Learning · Computer Science 2025-07-03 Liangyu Wang , Junxiao Wang , Jie Ren , Zihang Xiang , David E. Keyes , Di Wang

Applying machine learning (ML) to sensitive domains requires privacy protection of the underlying training data through formal privacy frameworks, such as differential privacy (DP). Yet, usually, the privacy of the training data comes at…

Machine Learning · Computer Science 2022-11-09 Franziska Boenisch , Christopher Mühl , Roy Rinberg , Jannis Ihrig , Adam Dziedzic

In a world where artificial intelligence and data science become omnipresent, data sharing is increasingly locking horns with data-privacy concerns. Differential privacy has emerged as a rigorous framework for protecting individual privacy…

Cryptography and Security · Computer Science 2022-06-06 March Boedihardjo , Thomas Strohmer , Roman Vershynin

We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning attacks, which we show correspond to realistic privacy attacks.…

Cryptography and Security · Computer Science 2020-06-16 Matthew Jagielski , Jonathan Ullman , Alina Oprea

Privacy concerns have led to a surge in the creation of synthetic datasets, with diffusion models emerging as a promising avenue. Although prior studies have performed empirical evaluations on these models, there has been a gap in providing…

Machine Learning · Computer Science 2024-06-04 Rongzhe Wei , Eleonora Kreačić , Haoyu Wang , Haoteng Yin , Eli Chien , Vamsi K. Potluru , Pan Li

We address the challenge of sample efficiency in differentially private fine-tuning of large language models (LLMs) using DP-SGD. While DP-SGD provides strong privacy guarantees, the added noise significantly increases the entropy of…

Machine Learning · Computer Science 2026-01-12 Ali Dadsetan , Frank Rudzicz

We revisit the problem of $n$-gram extraction in the differential privacy setting. In this problem, given a corpus of private text data, the goal is to release as many $n$-grams as possible while preserving user level privacy. Extracting…

Machine Learning · Computer Science 2021-08-09 Kunho Kim , Sivakanth Gopi , Janardhan Kulkarni , Sergey Yekhanin

Service providers of large language model (LLM) applications collect user instructions in the wild and use them in further aligning LLMs with users' intentions. These instructions, which potentially contain sensitive information, are…

Cryptography and Security · Computer Science 2024-07-03 Da Yu , Peter Kairouz , Sewoong Oh , Zheng Xu

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…

Cryptography and Security · Computer Science 2022-12-15 Jie Fu , Zhili Chen , XinPeng Ling

The need to analyze sensitive data, such as medical records or financial data, has created a critical research challenge in recent years. In this paper, we adopt the framework of differential privacy, and explore mechanisms for generating…

Cryptography and Security · Computer Science 2024-05-09 Nikolija Bojkovic , Po-Ling Loh

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…

Machine Learning · Computer Science 2025-10-29 Miguel Fernandez-de-Retana , Unai Zulaika , Rubén Sánchez-Corcuera , Aitor Almeida

When training a machine learning model with differential privacy, one sets a privacy budget. This budget represents a maximal privacy violation that any user is willing to face by contributing their data to the training set. We argue that…

Machine Learning · Computer Science 2024-01-22 Franziska Boenisch , Christopher Mühl , Adam Dziedzic , Roy Rinberg , Nicolas Papernot

Contextual bandit algorithms are useful in personalized online decision-making. However, many applications such as personalized medicine and online advertising require the utilization of individual-specific information for effective…

Machine Learning · Statistics 2021-06-08 Yuxuan Han , Zhipeng Liang , Yang Wang , Jiheng Zhang

Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning. It provides a single privacy guarantee to all datapoints in the dataset. We propose output-specific…

Machine Learning · Computer Science 2024-07-26 Da Yu , Gautam Kamath , Janardhan Kulkarni , Tie-Yan Liu , Jian Yin , Huishuai Zhang