English
Related papers

Related papers: Privacy Regularization: Joint Privacy-Utility Opti…

200 papers

As reinforcement learning techniques are increasingly applied to real-world decision problems, attention has turned to how these algorithms use potentially sensitive information. We consider the task of training a policy that maximizes…

Machine Learning · Computer Science 2024-04-17 Chris Cundy , Rishi Desai , Stefano Ermon

Privacy models were introduced in privacy-preserving data publishing and statistical disclosure control with the promise to end the need for costly empirical assessment of disclosure risk. We examine how well this promise is kept by the…

Cryptography and Security · Computer Science 2025-10-20 Josep Domingo-Ferrer , David Sánchez

The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…

Cryptography and Security · Computer Science 2024-12-10 Guoshenghui Zhao , Eric Song

Nowadays, the ubiquitous usage of mobile devices and networks have raised concerns about the loss of control over personal data and research advance towards the trade-off between privacy and utility in scenarios that combine exchange…

A privacy-utility tradeoff is developed for an arbitrary set of finite-alphabet source distributions. Privacy is quantified using differential privacy (DP), and utility is quantified using expected Hamming distortion maximized over the set…

Information Theory · Computer Science 2018-08-02 Kousha Kalantari , Lalitha Sankar , Anand Sarwate

Pre-trained Large Language Models (LLMs) are an integral part of modern AI that have led to breakthrough performances in complex AI tasks. Major AI companies with expensive infrastructures are able to develop and train these large models…

Cryptography and Security · Computer Science 2023-05-02 Rouzbeh Behnia , Mohamamdreza Ebrahimi , Jason Pacheco , Balaji Padmanabhan

Scaling laws have emerged as important components of large language model (LLM) training as they can predict performance gains through scale, and provide guidance on important hyper-parameter choices that would otherwise be expensive. LLMs…

Differential privacy (DP) in deep learning is a critical concern as it ensures the confidentiality of training data while maintaining model utility. Existing DP training algorithms provide privacy guarantees by clipping and then injecting…

Machine Learning · Computer Science 2025-04-02 Mingqian Feng , Zeliang Zhang , Jinyang Jiang , Yijie Peng , Chenliang Xu

We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set. Our mechanisms cluster the examples in the training…

Machine Learning · Computer Science 2021-10-06 Hossein Esfandiari , Vahab Mirrokni , Umar Syed , Sergei Vassilvitskii

Differential privacy (DP) provides rigorous privacy guarantees on individual's data while also allowing for accurate statistics to be conducted on the overall, sensitive dataset. To design a private system, first private algorithms must be…

Cryptography and Security · Computer Science 2020-11-19 Mark Cesar , Ryan Rogers

This research addresses privacy protection in Natural Language Processing (NLP) by introducing a novel algorithm based on differential privacy, aimed at safeguarding user data in common applications such as chatbots, sentiment analysis, and…

Cryptography and Security · Computer Science 2024-10-14 Shaobo Liu , Guiran Liu , Binrong Zhu , Yuanshuai Luo , Linxiao Wu , Rui Wang

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive…

Machine Learning · Statistics 2018-12-21 Martín Abadi , Andy Chu , Ian Goodfellow , H. Brendan McMahan , Ilya Mironov , Kunal Talwar , Li Zhang

Differentially private (DP) mechanisms face the challenge of providing accurate results while protecting their inputs: the privacy-utility trade-off. A simple but powerful technique for DP adds noise to sensitivity-bounded query outputs to…

Cryptography and Security · Computer Science 2021-07-28 David M. Sommer , Lukas Abfalterer , Sheila Zingg , Esfandiar Mohammadi

Recent developments in language modeling have increased their use in various applications and domains. Language models, often trained on sensitive data, can memorize and disclose this information during privacy attacks, raising concerns…

Computation and Language · Computer Science 2025-08-22 Pritilata Saha , Abhirup Sinha

Large organizations that collect data about populations (like the US Census Bureau) release summary statistics that are used by multiple stakeholders for resource allocation and policy making problems. These organizations are also legally…

Databases · Computer Science 2021-11-08 David Pujol , Yikai Wu , Brandon Fain , Ashwin Machanavajjhala

Large data collections required for the training of neural networks often contain sensitive information such as the medical histories of patients, and the privacy of the training data must be preserved. In this paper, we introduce a dropout…

Machine Learning · Statistics 2017-12-06 Beyza Ermis , Ali Taylan Cemgil

Differential privacy (DP) is the de facto standard for training machine learning (ML) models, including neural networks, while ensuring the privacy of individual examples in the training set. Despite a rich literature on how to train ML…

Machine Learning · Computer Science 2022-02-10 Alexey Kurakin , Shuang Song , Steve Chien , Roxana Geambasu , Andreas Terzis , Abhradeep Thakurta

Language models such as mBERT, XLM-R, and BLOOM aim to achieve multilingual generalization or compression to facilitate transfer to a large number of (potentially unseen) languages. However, these models should ideally also be private,…

Computation and Language · Computer Science 2023-08-21 Phillip Rust , Anders Søgaard

Applications of Differential Privacy (DP) in NLP must distinguish between the syntactic level on which a proposed mechanism operates, often taking the form of $\textit{word-level}$ or $\textit{document-level}$ privatization. Recently,…

Computation and Language · Computer Science 2024-07-02 Stephen Meisenbacher , Maulik Chevli , Florian Matthes

Ensuring the privacy of users whose data are used to train Natural Language Processing (NLP) models is necessary to build and maintain customer trust. Differential Privacy (DP) has emerged as the most successful method to protect the…

Cryptography and Security · Computer Science 2021-07-19 Ricardo Silva Carvalho , Theodore Vasiloudis , Oluwaseyi Feyisetan