English
Related papers

Related papers: Differentially-private text generation degrades ou…

200 papers

We initiate the study of language generation in the limit, a model recently introduced by Kleinberg and Mullainathan [KM24], under the constraint of differential privacy. We consider the continual release model, where a generator must…

Machine Learning · Statistics 2026-04-10 Anay Mehrotra , Grigoris Velegkas , Xifan Yu , Felix Zhou

There are concerns that the ability of language models (LMs) to generate high quality synthetic text can be misused to launch spam, disinformation, or propaganda. Therefore, the research community is actively working on developing…

Computation and Language · Computer Science 2021-06-04 Nirav Diwan , Tanmoy Chakravorty , Zubair Shafiq

Large language models (LLMs) are increasingly adapted to proprietary and domain-specific corpora that contain sensitive information, creating a tension between formal privacy guarantees and efficient deployment through model compression.…

Machine Learning · Computer Science 2026-04-07 Fatemeh Khadem , Sajad Mousavi , Yi Fang , Yuhong Liu

As deep learning-based, data-driven information extraction systems become increasingly integrated into modern document processing workflows, one primary concern is the risk of malicious leakage of sensitive private data from these systems.…

Cryptography and Security · Computer Science 2025-08-07 Saifullah Saifullah , Stefan Agne , Andreas Dengel , Sheraz Ahmed

Large language models trained on clinical text risk exposing sensitive patient information, yet differential privacy (DP) methods often severely degrade the diagnostic accuracy needed for deployment. Despite rapid progress in DP…

Machine Learning · Computer Science 2025-11-20 Mathieu Dufour , Andrew Duncan

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

The deployment of Machine-Generated Text (MGT) detection systems necessitates processing sensitive user data, creating a fundamental conflict between authorship verification and privacy preservation. Standard anonymization techniques often…

Cryptography and Security · Computer Science 2026-01-09 Lionel Z. Wang , Yusheng Zhao , Jiabin Luo , Xinfeng Li , Lixu Wang , Yinan Peng , Haoyang Li , XiaoFeng Wang , Wei Dong

Differentially private SGD (DPSGD) enables privacy-preserving training of language models, but often reduces utility, diversity, and linguistic quality. We introduce DPRefine, a three-phase method that initializes a model using data…

Machine Learning · Computer Science 2024-10-24 Ivoline C. Ngong , Joseph P. Near , Niloofar Mireshghallah

The success of large language models (LLMs) facilitate many parties to fine-tune LLMs on their own private data. However, this practice raises privacy concerns due to the memorization of LLMs. Existing solutions, such as utilizing synthetic…

Cryptography and Security · Computer Science 2024-10-11 Wenhao Wang , Xiaoyu Liang , Rui Ye , Jingyi Chai , Siheng Chen , Yanfeng Wang

Many works at the intersection of Differential Privacy (DP) in Natural Language Processing aim to protect privacy by transforming texts under DP guarantees. This can be performed in a variety of ways, from word perturbations to full…

Computation and Language · Computer Science 2025-08-29 Stephen Meisenbacher , Maulik Chevli , Florian Matthes

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Artificial Intelligence · Computer Science 2025-04-08 Hao Du , Shang Liu , Lele Zheng , Yang Cao , Atsuyoshi Nakamura , Lei Chen

With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outside their training data. For this purpose,…

Cryptography and Security · Computer Science 2025-11-13 Tatsuki Koga , Ruihan Wu , Zhiyuan Zhang , Kamalika Chaudhuri

Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for formal privacy guarantees, provides a principled framework for training LLMs with…

Machine Learning · Computer Science 2026-05-26 Enayat Ullah , Sai Aparna Aketi , Devansh Gupta , Huanyu Zhang , Meisam Razaviyayn

One of the big challenges in machine learning applications is that training data can be different from the real-world data faced by the algorithm. In language modeling, users' language (e.g. in private messaging) could change in a year and…

Computation and Language · Computer Science 2018-03-07 Vadim Popov , Mikhail Kudinov , Irina Piontkovskaya , Petr Vytovtov , Alex Nevidomsky

The application of Differential Privacy to Natural Language Processing techniques has emerged in relevance in recent years, with an increasing number of studies published in established NLP outlets. In particular, the adaptation of…

Computation and Language · Computer Science 2024-04-05 Stephen Meisenbacher , Nihildev Nandakumar , Alexandra Klymenko , Florian Matthes

Generative models trained with Differential Privacy (DP) are becoming increasingly prominent in the creation of synthetic data for downstream applications. Existing literature, however, primarily focuses on basic benchmarking datasets and…

Cryptography and Security · Computer Science 2024-02-08 Dingfan Chen , Marie Oestreich , Tejumade Afonja , Raouf Kerkouche , Matthias Becker , Mario Fritz

The capabilities of recent large language models (LLMs) to generate high-quality content indistinguishable by humans from human-written texts raises many concerns regarding their misuse. Previous research has shown that LLMs can be…

Computation and Language · Computer Science 2025-07-28 Aneta Zugecova , Dominik Macko , Ivan Srba , Robert Moro , Jakub Kopal , Katarina Marcincinova , Matus Mesarcik

Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high barrier for non-expert practitioners. Prior works either rely…

Machine Learning · Computer Science 2026-05-19 Erchi Wang , Pengrun Huang , Eli Chien , Om Thakkar , Kamalika Chaudhuri , Yu-Xiang Wang , Ruihan Wu

As the issues of privacy and trust are receiving increasing attention within the research community, various attempts have been made to anonymize textual data. A significant subset of these approaches incorporate differentially private…

Cryptography and Security · Computer Science 2022-05-05 Justus Mattern , Benjamin Weggenmann , Florian Kerschbaum

Accurately learning from user data while ensuring quantifiable privacy guarantees provides an opportunity to build better Machine Learning (ML) models while maintaining user trust. Recent literature has demonstrated the applicability of a…

Machine Learning · Computer Science 2020-12-11 Oluwaseyi Feyisetan , Abhinav Aggarwal , Zekun Xu , Nathanael Teissier