English
Related papers

Related papers: NoEsis: Differentially Private Knowledge Transfer …

200 papers

We study private prediction where differential privacy is achieved by adding noise to the outputs of a non-private model. Existing methods rely on noise proportional to the global sensitivity of the model, often resulting in sub-optimal…

The advancement of large language models (LLMs) brings notable improvements across various applications, while simultaneously raising concerns about potential private data exposure. One notable capability of LLMs is their ability to form…

Computation and Language · Computer Science 2024-02-12 Hanyin Shao , Jie Huang , Shen Zheng , Kevin Chen-Chuan Chang

Federated Learning (FL) is a widely adopted privacy-preserving machine learning approach where private data remains local, enabling secure computations and the exchange of local model gradients between local clients and third-party…

Machine Learning · Computer Science 2025-08-04 Hanchi Ren , Jingjing Deng , Xianghua Xie

As Large Language Models (LLMs) proliferate, developing privacy safeguards for these models is crucial. One popular safeguard involves training LLMs in a differentially private manner. However, such solutions are shown to be computationally…

Machine Learning · Computer Science 2024-10-04 James Flemings , Meisam Razaviyayn , Murali Annavaram

We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the private examples demonstrated in the prompt. We propose a novel…

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…

Machine Learning · Computer Science 2022-10-27 Justus Mattern , Zhijing Jin , Benjamin Weggenmann , Bernhard Schoelkopf , Mrinmaya Sachan

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

There is an increasing concern that most current published research findings are false. The main cause seems to lie in the fundamental disconnection between theory and practice in data analysis. While the former typically relies on…

Machine Learning · Statistics 2019-03-06 Amedeo Roberto Esposito , Michael Gastpar , Ibrahim Issa

With LLMs increasingly deployed in corporate data management, it is crucial to ensure that these models do not leak sensitive information. In the context of corporate data management, the concept of sensitivity awareness has been…

Cryptography and Security · Computer Science 2026-01-30 Dren Fazlija , Iyiola E. Olatunji , Daniel Kudenko , Sandipan Sikdar

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

SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sensitive information, fine-tune on proprietary recordings, or both. We identify and…

Computation and Language · Computer Science 2026-05-28 Maike Züfle , Jan Niehues

Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized…

Machine Learning · Computer Science 2025-10-08 Hanbo Huang , Yihan Li , Bowen Jiang , Bo Jiang , Lin Liu , Ruoyu Sun , Zhuotao Liu , Shiyu Liang

With the increasing applications of language models, it has become crucial to protect these models from leaking private information. Previous work has attempted to tackle this challenge by training RNN-based language models with…

Computation and Language · Computer Science 2022-07-19 Weiyan Shi , Aiqi Cui , Evan Li , Ruoxi Jia , Zhou Yu

We study the problem of estimating high dimensional models with underlying sparse structures while preserving the privacy of each training example. We develop a differentially private high-dimensional sparse learning framework using the…

Machine Learning · Statistics 2019-09-16 Lingxiao Wang , Quanquan Gu

Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many…

Machine Learning · Computer Science 2020-06-26 Lingjuan Lyu , Yitong Li , Xuanli He , Tong Xiao

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with…

Cryptography and Security · Computer Science 2021-02-24 Huseyin A. Inan , Osman Ramadan , Lukas Wutschitz , Daniel Jones , Victor Rühle , James Withers , Robert Sim

Federated Learning (FL) enables collaborative training of models across distributed clients without sharing local data, addressing privacy concerns in decentralized systems. However, the gradient-sharing process exposes private data to…

Machine Learning · Computer Science 2025-03-11 Mingcong Xu , Xiaojin Zhang , Wei Chen , Hai Jin

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing but also pose significant privacy risks by memorizing and leaking Personally Identifiable Information (PII). Existing mitigation…

Machine Learning · Computer Science 2025-03-17 Ahmed Frikha , Muhammad Reza Ar Razi , Krishna Kanth Nakka , Ricardo Mendes , Xue Jiang , Xuebing Zhou

As language models (LMs) are widely utilized in personalized communication scenarios (e.g., sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in accordance with the contextual privacy…

Computation and Language · Computer Science 2025-03-17 Yijia Shao , Tianshi Li , Weiyan Shi , Yanchen Liu , Diyi Yang

Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many knowledge editing…