English
Related papers

Related papers: How reparametrization trick broke differentially-p…

200 papers

We propose the notion of empirical privacy variance and study it in the context of differentially private fine-tuning of language models. Specifically, we show that models calibrated to the same $(\varepsilon, \delta)$-DP guarantee using…

Machine Learning · Computer Science 2025-05-27 Yuzheng Hu , Fan Wu , Ruicheng Xian , Yuhang Liu , Lydia Zakynthinou , Pritish Kamath , Chiyuan Zhang , David Forsyth

Differential privacy is a formal, mathematical definition of data privacy that has gained traction in academia, industry, and government. The task of correctly constructing differentially private algorithms is non-trivial, and mistakes have…

Cryptography and Security · Computer Science 2021-01-05 Subhajit Roy , Justin Hsu , Aws Albarghouthi

Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT. In this work, we…

Machine Learning · Computer Science 2024-05-06 Fan Wu , Huseyin A. Inan , Arturs Backurs , Varun Chandrasekaran , Janardhan Kulkarni , Robert Sim

Communication lays the foundation for cooperation in human society and in multi-agent reinforcement learning (MARL). Humans also desire to maintain their privacy when communicating with others, yet such privacy concern has not been…

Machine Learning · Computer Science 2023-08-22 Canzhe Zhao , Yanjie Ze , Jing Dong , Baoxiang Wang , Shuai Li

Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for hidden semantic discovery of text data and serves as a fundamental tool for text analysis in various applications. However, the LDA model as well as the training…

Machine Learning · Computer Science 2020-10-12 Fangyuan Zhao , Xuebin Ren , Shusen Yang , Qing Han , Peng Zhao , Xinyu Yang

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding them in external knowledge. However, its application in sensitive domains is limited by privacy risks. Existing private RAG methods typically rely on…

Cryptography and Security · Computer Science 2026-05-13 Junki Mori , Kazuya Kakizaki , Taiki Miyagawa , Jun Sakuma

The deployment of deep learning applications has to address the growing privacy concerns when using private and sensitive data for training. A conventional deep learning model is prone to privacy attacks that can recover the sensitive…

Cryptography and Security · Computer Science 2020-04-10 Di Gao , Cheng Zhuo

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

Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning…

Cryptography and Security · Computer Science 2025-03-12 Haodi Wang , Tangyu Jiang , Yu Guo , Chengjun Cai , Cong Wang , Xiaohua Jia

The central question studied in this paper is Renyi Differential Privacy (RDP) guarantees for general discrete local mechanisms in the shuffle privacy model. In the shuffle model, each of the $n$ clients randomizes its response using a…

Cryptography and Security · Computer Science 2021-05-12 Antonious M. Girgis , Deepesh Data , Suhas Diggavi , Ananda Theertha Suresh , Peter Kairouz

Text data has become extremely valuable due to the emergence of machine learning algorithms that learn from it. A lot of high-quality text data generated in the real world is private and therefore cannot be shared or used freely due to…

Computation and Language · Computer Science 2024-07-25 Chulin Xie , Zinan Lin , Arturs Backurs , Sivakanth Gopi , Da Yu , Huseyin A Inan , Harsha Nori , Haotian Jiang , Huishuai Zhang , Yin Tat Lee , Bo Li , Sergey Yekhanin

Differential privacy (DP) is the de facto privacy standard against privacy leakage attacks, including many recently discovered ones against large language models (LLMs). However, we discovered that LLMs could reconstruct the altered/removed…

Cryptography and Security · Computer Science 2025-09-19 Shuchao Pang , Zhigang Lu , Haichen Wang , Peng Fu , Yongbin Zhou , Minhui Xue

Training machine learning models based on neural networks requires large datasets, which may contain sensitive information. The models, however, should not expose private information from these datasets. Differentially private SGD [DP-SGD]…

Machine Learning · Computer Science 2024-09-26 Francisco Aguilera-Martínez , Fernando Berzal

Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products. Yet applying differential privacy (DP), a canonical notion with provable privacy guarantees for machine…

Computation and Language · Computer Science 2022-10-28 Weiyan Shi , Ryan Shea , Si Chen , Chiyuan Zhang , Ruoxi Jia , Zhou Yu

Achieving differential privacy (DP) guarantees in fully decentralized machine learning is challenging due to the absence of a central aggregator and varying trust assumptions among nodes. We present a framework for DP analysis of…

Machine Learning · Computer Science 2026-02-06 Antti Koskela , Tejas Kulkarni

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

Differentially private (DP) optimization is the standard paradigm to learn large neural networks that are accurate and privacy-preserving. The computational cost for DP deep learning, however, is notoriously heavy due to the per-sample…

Machine Learning · Computer Science 2023-09-20 Zhiqi Bu , Yu-Xiang Wang , Sheng Zha , George Karypis

As privacy issues are receiving increasing attention within the Natural Language Processing (NLP) community, numerous methods have been proposed to sanitize texts subject to differential privacy. However, the state-of-the-art text…

Cryptography and Security · Computer Science 2023-09-04 Huimin Chen , Fengran Mo , Yanhao Wang , Cen Chen , Jian-Yun Nie , Chengyu Wang , Jamie Cui

Reinforcement learning algorithms are widely used in domains where it is desirable to provide a personalized service. In these domains it is common that user data contains sensitive information that needs to be protected from third parties.…

Machine Learning · Computer Science 2021-10-28 Evrard Garcelon , Vianney Perchet , Ciara Pike-Burke , Matteo Pirotta

In recent years, local differential privacy (LDP) has emerged as a technique of choice for privacy-preserving data collection in several scenarios when the aggregator is not trustworthy. LDP provides client-side privacy by adding noise at…

Machine Learning · Statistics 2021-10-28 Tejas Kulkarni , Joonas Jälkö , Samuel Kaski , Antti Honkela