English
Related papers

Related papers: Private Language Models via Truncated Laplacian Me…

200 papers

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

In federated learning collaborative learning takes place by a set of clients who each want to remain in control of how their local training data is used, in particular, how can each client's local training data remain private? Differential…

Machine Learning · Computer Science 2023-07-18 Marten van Dijk , Phuong Ha Nguyen

Deep neural networks often use large, high-quality datasets to achieve high performance on many machine learning tasks. When training involves potentially sensitive data, this process can raise privacy concerns, as large models have been…

Machine Learning · Computer Science 2025-06-23 Felix Zhou , Samson Zhou , Vahab Mirrokni , Alessandro Epasto , Vincent Cohen-Addad

Differential privacy (DP) is a formal notion for quantifying the privacy loss of algorithms. Algorithms in the central model of DP achieve high accuracy but make the strongest trust assumptions whereas those in the local DP model make the…

Cryptography and Security · Computer Science 2021-06-09 Badih Ghazi , Ravi Kumar , Pasin Manurangsi , Rasmus Pagh

Noisy gradient descent and its variants are the predominant algorithms for differentially private machine learning. It is a fundamental question to quantify their privacy leakage, yet tight characterizations remain open even in the…

Machine Learning · Computer Science 2024-06-13 Jinho Bok , Weijie Su , Jason M. Altschuler

Large Language Models (LLMs) excel in natural language understanding by capturing hidden semantics in vector space. This process enriches the value of text embeddings for various downstream tasks, thereby fostering the…

Artificial Intelligence · Computer Science 2024-08-28 Peihua Mai , Ran Yan , Zhe Huang , Youjia Yang , Yan Pang

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

We design new differentially private algorithms for the Euclidean k-means problem, both in the centralized model and in the local model of differential privacy. In both models, our algorithms achieve significantly improved error guarantees…

Data Structures and Algorithms · Computer Science 2018-07-17 Haim Kaplan , Uri Stemmer

Differential privacy is the state-of-the-art formal definition for data release under strong privacy guarantees. A variety of mechanisms have been proposed in the literature for releasing the output of numeric queries (e.g., the Laplace…

Cryptography and Security · Computer Science 2022-04-15 Victor A. E. Farias , Felipe T. Brito , Cheryl Flynn , Javam C. Machado , Subhabrata Majumdar , Divesh Srivastava

Much of the literature on differential privacy focuses on item-level privacy, where loosely speaking, the goal is to provide privacy per item or training example. However, recently many practical applications such as federated learning…

Machine Learning · Computer Science 2021-01-13 Yuhan Liu , Ananda Theertha Suresh , Felix Yu , Sanjiv Kumar , Michael Riley

A major challenge in applying differential privacy to training deep neural network models is scalability.The widely-used training algorithm, differentially private stochastic gradient descent (DP-SGD), struggles with training…

Machine Learning · Computer Science 2023-03-09 Kamil Adamczewski , Mijung Park

We present an approach for generating differentially private synthetic text using large language models (LLMs), via private prediction. In the private prediction framework, we only require the output synthetic data to satisfy differential…

Machine Learning · Computer Science 2024-10-10 Kareem Amin , Alex Bie , Weiwei Kong , Alexey Kurakin , Natalia Ponomareva , Umar Syed , Andreas Terzis , Sergei Vassilvitskii

In this paper, an adjustment to the original differentially private stochastic gradient descent (DPSGD) algorithm for deep learning models is proposed. As a matter of motivation, to date, almost no state-of-the-art machine learning…

Machine Learning · Computer Science 2021-07-13 Mehdi Amian

Graph Neural Networks have achieved tremendous success in modeling complex graph data in a variety of applications. However, there are limited studies investigating privacy protection in GNNs. In this work, we propose a learning framework…

Machine Learning · Computer Science 2024-08-07 Karuna Bhaila , Wen Huang , Yongkai Wu , Xintao Wu

Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…

Machine Learning · Statistics 2022-10-18 Jiayuan Ye , Reza Shokri

Text embeddings enable numerous NLP applications but face severe privacy risks from embedding inversion attacks, which can expose sensitive attributes or reconstruct raw text. Existing differential privacy defenses assume uniform…

Cryptography and Security · Computer Science 2026-02-10 Yu-Che Tsai , Hsiang Hsiao , Kuan-Yu Chen , Shou-De Lin

The shuffle model of local differential privacy is an advanced method of privacy amplification designed to enhance privacy protection with high utility. It achieves this by randomly shuffling sensitive data, making linking individual data…

Cryptography and Security · Computer Science 2024-03-04 E Chen , Yang Cao , Yifei Ge

Local differential privacy (LDP) has become a central topic in data privacy research, offering strong privacy guarantees by perturbing user data at the source and removing the need for a trusted curator. However, the noise introduced by LDP…

Machine Learning · Computer Science 2026-03-04 Caihong Qin , Yang Bai

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…

Machine Learning · Computer Science 2025-10-29 Miguel Fernandez-de-Retana , Unai Zulaika , Rubén Sánchez-Corcuera , Aitor Almeida

Popular approaches to differential privacy, such as the Laplace and exponential mechanisms, calibrate randomised smoothing through global sensitivity of the target non-private function. Bounding such sensitivity is often a prohibitively…

Machine Learning · Computer Science 2017-06-12 Benjamin I. P. Rubinstein , Francesco Aldà
‹ Prev 1 8 9 10 Next ›