English
Related papers

Related papers: Research Challenges in Designing Differentially Pr…

200 papers

Federated learning has emerged as an attractive approach to protect data privacy by eliminating the need for sharing clients' data while reducing communication costs compared with centralized machine learning algorithms. However, recent…

In-context learning (ICL)-the ability of transformer-based models to perform new tasks from examples provided at inference time-has emerged as a hallmark of modern language models. While recent works have investigated the mechanisms…

Machine Learning · Statistics 2025-04-23 Soham Bonnerjee , Zhen Wei , Yeon , Anna Asch , Sagnik Nandy , Promit Ghosal

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

Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns (Dwork et al., 2014).…

Cryptography and Security · Computer Science 2021-02-03 Satyapriya Krishna , Rahul Gupta , Christophe Dupuy

This paper introduces a conversational interface system that enables participatory design of differentially private AI systems in public sector applications. Addressing the challenge of balancing mathematical privacy guarantees with…

Information Theory · Computer Science 2025-05-28 Wenjun Yang , Eyhab Al-Masri

Ensuring differential privacy of models learned from sensitive user data is an important goal that has been studied extensively in recent years. It is now known that for some basic learning problems, especially those involving…

Machine Learning · Computer Science 2018-05-10 Cynthia Dwork , Vitaly Feldman

Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and output perturbation.…

Cryptography and Security · Computer Science 2022-04-28 Zhigang Lu , Hassan Jameel Asghar , Mohamed Ali Kaafar , Darren Webb , Peter Dickinson

We consider the setting where a user with sensitive features wishes to obtain a recommendation from a server in a differentially private fashion. We propose a ``multi-selection'' architecture where the server can send back multiple…

Data Structures and Algorithms · Computer Science 2024-07-23 Ashish Goel , Zhihao Jiang , Aleksandra Korolova , Kamesh Munagala , Sahasrajit Sarmasarkar

Language models are capable of memorizing detailed patterns and information, leading to a double-edged effect: they achieve impressive modeling performance on downstream tasks with the stored knowledge but also raise significant privacy…

Artificial Intelligence · Computer Science 2024-10-07 Xianzhi Li , Ran Zmigrod , Zhiqiang Ma , Xiaomo Liu , Xiaodan Zhu

Machine learning (ML) models frequently rely on training data that may include sensitive or personal information, raising substantial privacy concerns. Legislative frameworks such as the General Data Protection Regulation (GDPR) and the…

Machine Learning · Computer Science 2024-12-31 Md Mahadi Hasan Nahid , Sadid Bin Hasan

Mobile apps and location-based services generate large amounts of location data that can benefit research on traffic optimization, context-aware notifications and public health (e.g., spread of contagious diseases). To preserve individual…

Databases · Computer Science 2021-08-04 Sepanta Zeighami , Ritesh Ahuja , Gabriel Ghinita , Cyrus Shahabi

Generative adversarial network (GAN) has attracted increasing attention recently owing to its impressive ability to generate realistic samples with high privacy protection. Without directly interactive with training examples, the generative…

Machine Learning · Computer Science 2020-07-07 Chuan Ma , Jun Li , Ming Ding , Bo Liu , Kang Wei , Jian Weng , H. Vincent Poor

Preserving differential privacy has been well studied under centralized setting. However, it's very challenging to preserve differential privacy under multiparty setting, especially for the vertically partitioned case. In this work, we…

Machine Learning · Computer Science 2019-11-13 Depeng Xu , Shuhan Yuan , Xintao Wu

Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal…

Machine Learning · Computer Science 2026-05-19 Haichao Sha , Zihao Wang , Yuncheng Wu , Hong Chen , Wei Dong

Differentially private data generation techniques have become a promising solution to the data privacy challenge -- it enables sharing of data while complying with rigorous privacy guarantees, which is essential for scientific progress in…

Cryptography and Security · Computer Science 2022-11-09 Dingfan Chen , Raouf Kerkouche , Mario Fritz

The generative Artificial Intelligence (AI) tools based on Large Language Models (LLMs) use billions of parameters to extensively analyse large datasets and extract critical private information such as, context, specific details,…

Cryptography and Security · Computer Science 2023-10-20 Imdad Ullah , Najm Hassan , Sukhpal Singh Gill , Basem Suleiman , Tariq Ahamed Ahanger , Zawar Shah , Junaid Qadir , Salil S. Kanhere

Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data. This paper focuses on a class of regularized empirical risk minimization (ERM) machine learning problems, and develops…

Machine Learning · Computer Science 2016-03-11 Tao Zhang , Quanyan Zhu

Planning is one of the main approaches used to improve agents' working efficiency by making plans beforehand. However, during planning, agents face the risk of having their private information leaked. This paper proposes a novel strong…

Artificial Intelligence · Computer Science 2022-12-06 Dayong Ye , Tianqing Zhu , Sheng Shen , Wanlei Zhou , Philip S. Yu

We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of deep…

Machine Learning · Computer Science 2018-02-27 H. Brendan McMahan , Daniel Ramage , Kunal Talwar , Li Zhang

Linear regression is an important tool across many fields that work with sensitive human-sourced data. Significant prior work has focused on producing differentially private point estimates, which provide a privacy guarantee to individuals…

Machine Learning · Computer Science 2019-10-30 Garrett Bernstein , Daniel Sheldon