English
Related papers

Related papers: Hidden-State Privacy Has an Empty Middle

200 papers

We propose differentially private algorithms for parameter estimation in both low-dimensional and high-dimensional sparse generalized linear models (GLMs) by constructing private versions of projected gradient descent. We show that the…

Machine Learning · Statistics 2020-12-08 T. Tony Cai , Yichen Wang , Linjun Zhang

Differentially private stochastic gradient descent (DP-SGD) adds noise to gradients in back-propagation, safeguarding training data from privacy leakage, particularly membership inference. It fails to cover (inference-time) threats like…

Cryptography and Security · Computer Science 2023-09-20 Minxin Du , Xiang Yue , Sherman S. M. Chow , Tianhao Wang , Chenyu Huang , Huan Sun

A user's data is represented by a Gaussian random variable. Given a linear function of the data, a querier is required to recover, with at least a prescribed accuracy level, the function value based on a query response provided by the user.…

Information Theory · Computer Science 2023-06-30 Ajaykrishnan Nageswaran

Differentially Private Stochastic Gradient Descent (DP-SGD) and its variants have been proposed to ensure rigorous privacy for fine-tuning large-scale pre-trained language models. However, they rely heavily on the Gaussian mechanism, which…

Cryptography and Security · Computer Science 2024-05-30 Qin Yang , Meisam Mohammad , Han Wang , Ali Payani , Ashish Kundu , Kai Shu , Yan Yan , Yuan Hong

The data transmitted by cyber-physical systems can be intercepted and exploited by malicious individuals to infer privacy-sensitive information regarding the physical system. This motivates us to study the problem of preserving privacy in…

Systems and Control · Electrical Eng. & Systems 2023-04-04 Teimour Hosseinalizadeh , Nima Monshizadeh

We present a fast, differentially private algorithm for high-dimensional covariance-aware mean estimation with nearly optimal sample complexity. Only exponential-time estimators were previously known to achieve this guarantee. Given $n$…

Machine Learning · Computer Science 2025-11-26 Gavin Brown , Samuel B. Hopkins , Adam Smith

This paper develops a framework for differentially private $e$-values under Gaussian differential privacy ($\mu$-GDP). We characterize the canonical noise mechanism, establishing that optimal multiplicative perturbation follows a Gaussian…

Methodology · Statistics 2026-05-29 Qi Kuang , Bowen Gang , Yin Xia

This paper considers the two-user Gaussian interference channel in the presence of adversarial jammers. We first provide a general model including an arbitrary number of jammers, and show that its capacity region is equivalent to that of a…

Information Theory · Computer Science 2017-12-13 Fatemeh Hosseinigoki , Oliver Kosut

We study the problem of continually releasing statistics of an evolving dataset under differential privacy. In the event-level setting, we show the first polynomial lower bounds on the additive error for insertions-only graph problems such…

Data Structures and Algorithms · Computer Science 2025-12-19 Bardiya Aryanfard , Monika Henzinger , David Saulpic , A. R. Sricharan

To reduce the communication cost of differential privacy mechanisms, we introduce a novel construction, called Poisson private representation (PPR), designed to compress and simulate any local randomizer while ensuring local differential…

Cryptography and Security · Computer Science 2024-11-12 Yanxiao Liu , Wei-Ning Chen , Ayfer Özgür , Cheuk Ting Li

We study a symmetric Gaussian wiretap channel with a helper, where a confidential message is sent from a transmitter to a legitimate receiver, in the presence of a helper and an eavesdropper, under a weak notion of secrecy constraint. For…

Information Theory · Computer Science 2019-09-12 Jinyuan Chen , Chunhua Geng

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

It is difficult to continually update private machine learning models with new data while maintaining privacy. Data incur increasing privacy loss -- as measured by differential privacy -- when they are used in repeated computations. In this…

Machine Learning · Computer Science 2022-03-08 Lauren Watson , Abhirup Ghosh , Benedek Rozemberczki , Rik Sarkar

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

We consider the problem of learning high-dimensional, nonparametric and structured (e.g. Gaussian) distributions in distributed networks, where each node in the network observes an independent sample from the underlying distribution and can…

Information Theory · Computer Science 2019-06-04 Leighton Pate Barnes , Yanjun Han , Ayfer Ozgur

This paper studies distributed stochastic nonconvex optimization problems with compressed communication and differential privacy, in which each agent aims to minimize the sum of all agents' cost functions by using local compressed…

Optimization and Control · Mathematics 2026-03-24 Antai Xie , Xiaoqiang Ren , Xinlei Yi , Tao Yang , Xiaofan Wang

We consider the problem of publicly releasing a dataset for support vector machine classification while not infringing on the privacy of data subjects (i.e., individuals whose private information is stored in the dataset). The dataset is…

Cryptography and Security · Computer Science 2020-01-01 Farhad Farokhi

We propose a Bayesian pseudo posterior mechanism to generate record-level synthetic databases equipped with an $(\epsilon,\delta)-$ probabilistic differential privacy (pDP) guarantee, where $\delta$ denotes the probability that any observed…

Methodology · Statistics 2021-08-17 Terrance D. Savitsky , Matthew R. Williams , Jingchen Hu

The first large-scale deployment of private federated learning uses differentially private counting in the continual release model as a subroutine (Google AI blog titled "Federated Learning with Formal Differential Privacy Guarantees"). In…

Machine Learning · Computer Science 2024-02-06 Monika Henzinger , Jalaj Upadhyay , Sarvagya Upadhyay

The gold standard for privacy in machine learning, Differential Privacy (DP), is often interpreted through its guarantees against membership inference. However, translating DP budgets into quantitative protection against the more damaging…