English
Related papers

Related papers: Enhancing One-run Privacy Auditing with Quantile R…

200 papers

We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning attacks, which we show correspond to realistic privacy attacks.…

Cryptography and Security · Computer Science 2020-06-16 Matthew Jagielski , Jonathan Ullman , Alina Oprea

Membership inference attacks (MIAs) aim to determine whether specific data were used to train a model. While extensively studied on classification models, their impact on time series forecasting remains largely unexplored. We address this…

Machine Learning · Computer Science 2026-02-13 Nicolas Johansson , Tobias Olsson , Daniel Nilsson , Johan Östman , Fazeleh Hoseini

Given a group size m and a sensitive dataset D, group privacy (GP) releases information about D with the guarantee that the adversary cannot infer with high confidence whether the underlying data is D or a neighboring dataset D' that…

Cryptography and Security · Computer Science 2024-08-27 Yangfan Jiang , Xinjian Luo , Yin Yang , Xiaokui Xiao

Large organizations that collect data about populations (like the US Census Bureau) release summary statistics that are used by multiple stakeholders for resource allocation and policy making problems. These organizations are also legally…

Databases · Computer Science 2021-11-08 David Pujol , Yikai Wu , Brandon Fain , Ashwin Machanavajjhala

Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privacy (DP) to protect sensitive data, their sensitivity to…

Machine Learning · Computer Science 2025-09-04 Ilana Sebag , Jean-Yves Franceschi , Alain Rakotomamonjy , Alexandre Allauzen , Jamal Atif

We study the problem of performing counting queries at different levels in hierarchical structures while preserving individuals' privacy. Motivated by applications, we propose a new error measure for this problem by considering a…

Data Structures and Algorithms · Computer Science 2023-04-28 Badih Ghazi , Pritish Kamath , Ravi Kumar , Pasin Manurangsi , Kewen Wu

Foundation-style ECG encoders pretrained with self-supervised learning are increasingly reused across tasks, institutions, and deployment contexts, often through model-as-a-service interfaces that expose scalar scores or latent…

Ensuring the privacy of sensitive training data is crucial in privacy-preserving machine learning. However, in practical scenarios, privacy protection may be required for only a subset of features. For instance, in ICU data, demographic…

Machine Learning · Computer Science 2025-11-07 Linghui Zeng , Ruixuan Liu , Atiquer Rahman Sarkar , Xiaoqian Jiang , Joyce C. Ho , Li Xiong

Individual privacy accounting enables bounding differential privacy (DP) loss individually for each participant involved in the analysis. This can be informative as often the individual privacy losses are considerably smaller than those…

Cryptography and Security · Computer Science 2023-08-25 Antti Koskela , Marlon Tobaben , Antti Honkela

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to protect sensitive data during the training of machine learning models, but its privacy guarantee often comes at a large cost of model performance due to the lack…

Machine Learning · Computer Science 2026-01-16 Hao Liang , Wanrong Zhang , Xinlei He , Kaishun Wu , Hong Xing

To protect privacy for data-collection-based services, local differential privacy (LDP) is widely adopted due to its rigorous theoretical bound on privacy loss. However, mistakes in complex theoretical analysis or subtle implementation…

Cryptography and Security · Computer Science 2025-08-18 Jingnan Xu , Leixia Wang , Xiaofeng Meng

Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of the training set. While existing methods typically rely on measuring reconstruction error across…

Machine Learning · Computer Science 2026-04-27 Mingxing Rao , Bowen Qu , Daniel Moyer

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

Privacy preservation in machine learning, particularly through Differentially Private Stochastic Gradient Descent (DP-SGD), is critical for sensitive data analysis. However, existing statistical inference methods for SGD predominantly focus…

Machine Learning · Statistics 2025-12-15 Xintao Xia , Linjun Zhang , Zhanrui Cai

This work proposes an algorithmic method to verify differential privacy for estimation mechanisms with performance guarantees. Differential privacy makes it hard to distinguish outputs of a mechanism produced by adjacent inputs. While…

Systems and Control · Electrical Eng. & Systems 2021-12-03 Yunhai Han , Sonia Martínez

Nowadays, machine learning models and applications have become increasingly pervasive. With this rapid increase in the development and employment of machine learning models, a concern regarding privacy has risen. Thus, there is a legitimate…

Machine Learning · Computer Science 2022-11-22 Samah Baraheem , Zhongmei Yao

Machine learning (ML) models can memorize training datasets. As a result, training ML models over private datasets can lead to the violation of individuals' privacy. Differential privacy (DP) is a rigorous privacy notion to preserve the…

Machine Learning · Computer Science 2024-02-13 Mohammad Hoseinpour , Milad Hoseinpour , Ali Aghagolzadeh

Differentially private (DP) machine learning has recently become popular. The privacy loss of DP algorithms is commonly reported using $(\varepsilon,\delta)$-DP. In this paper, we propose a numerical accountant for evaluating the privacy…

Machine Learning · Statistics 2020-08-28 Antti Koskela , Joonas Jälkö , Antti Honkela

Membership inference attacks (MIAs) test whether a data point was part of a model's training set, posing serious privacy risks. Existing methods often depend on shadow models or heavy query access, which limits their practicality. We…

Machine Learning · Computer Science 2025-10-28 Yongchao Huang , Pengfei Zhang , Shahzad Mumtaz

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