English
Related papers

Related papers: A Blessing of Dimensionality in Membership Inferen…

200 papers

In this work, we systematically explore the data privacy issues of dataset pruning in machine learning systems. Our findings reveal, for the first time, that even if data in the redundant set is solely used before model training, its…

Cryptography and Security · Computer Science 2024-11-26 Qi Li , Cheng-Long Wang , Yinzhi Cao , Di Wang

Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…

Cryptography and Security · Computer Science 2026-02-03 Marlon Tobaben , Hibiki Ito , Joonas Jälkö , Yuan He , Antti Honkela

Differential privacy is a mathematical framework for privacy-preserving data analysis. Changing the hyperparameters of a differentially private algorithm allows one to trade off privacy and utility in a principled way. Quantifying this…

Machine Learning · Statistics 2020-07-23 Brendan Avent , Javier Gonzalez , Tom Diethe , Andrei Paleyes , Borja Balle

Text-to-image diffusion models have demonstrated remarkable capabilities in creating images highly aligned with user prompts, yet their proclivity for memorizing training set images has sparked concerns about the originality of the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Chen Chen , Daochang Liu , Mubarak Shah , Chang Xu

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

A deep learning model usually has to sacrifice some utilities when it acquires some other abilities or characteristics. Privacy preservation has such trade-off relationships with utilities. The loss disparity between various defense…

Machine Learning · Computer Science 2026-02-10 Xingli Fang , Jung-Eun Kim

Data engineering often requires accuracy (utility) constraints on results, posing significant challenges in designing differentially private (DP) mechanisms, particularly under stringent privacy parameter $\epsilon$. In this paper, we…

Cryptography and Security · Computer Science 2024-12-17 Bo Jiang , Wanrong Zhang , Donghang Lu , Jian Du , Sagar Sharma , Qiang Yan

Regularization methods allow one to handle a variety of inferential problems where there are more covariates than cases. This allows one to consider a potentially enormous number of covariates for a problem. We exploit the power of these…

Methodology · Statistics 2012-10-03 Yoonkyung Lee , Steven N. MacEachern , Yoonsuh Jung

Federated learning has emerged as a promising paradigm for collaborative model training while preserving data privacy. However, recent studies have shown that it is vulnerable to various privacy attacks, such as data reconstruction attacks.…

Cryptography and Security · Computer Science 2024-07-25 Xiaojin Zhang , Wei Chen

Differential privacy is often applied with a privacy parameter that is larger than the theory suggests is ideal; various informal justifications for tolerating large privacy parameters have been proposed. In this work, we consider partial…

Cryptography and Security · Computer Science 2022-09-12 Badih Ghazi , Ravi Kumar , Pasin Manurangsi , Thomas Steinke

The paper is concerned with inference for a parameter of interest in models that share a common interpretation for that parameter but that may differ appreciably in other respects. We study the general structure of models under which the…

Statistics Theory · Mathematics 2024-08-06 Heather Battey , Nancy Reid

Private regression has received attention from both database and security communities. Recent work by Fredrikson et al. (USENIX Security 2014) analyzed the functional mechanism (Zhang et al. VLDB 2012) for training linear regression models…

Cryptography and Security · Computer Science 2015-12-22 Xi Wu , Matthew Fredrikson , Wentao Wu , Somesh Jha , Jeffrey F. Naughton

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This article provides theoretical guarantees by exploring the…

Machine Learning · Statistics 2025-10-08 Eric Aubinais , Elisabeth Gassiat , Pablo Piantanida

Federated Learning (FL) is a novel privacy-protection distributed machine learning paradigm that guarantees user privacy and prevents the risk of data leakage due to the advantage of the client's local training. Researchers have struggled…

Machine Learning · Computer Science 2023-12-01 Kangkang Sun , Xiaojin Zhang , Xi Lin , Gaolei Li , Jing Wang , Jianhua Li

Federated learning is a decentralized machine learning approach where clients train models locally and share model updates to develop a global model. This enables low-resource devices to collaboratively build a high-quality model without…

Cryptography and Security · Computer Science 2024-12-10 Li Bai , Haibo Hu , Qingqing Ye , Haoyang Li , Leixia Wang , Jianliang Xu

Deep learning has achieved overwhelming success, spanning from discriminative models to generative models. In particular, deep generative models have facilitated a new level of performance in a myriad of areas, ranging from media…

Machine Learning · Computer Science 2020-11-24 Dingfan Chen , Ning Yu , Yang Zhang , Mario Fritz

This paper studies the statistical characterization of detecting an adversary who wants to harm some computation such as machine learning models or aggregation by altering the output of a differentially private mechanism in addition to…

Information Theory · Computer Science 2021-06-28 Ayşe Ünsal , Melek Önen

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

Cryptography and Security · Computer Science 2025-05-02 Hao Du , Shang Liu , Yang Cao

For scalable machine learning on large data sets, subsampling a representative subset is a common approach for efficient model training. This is often achieved through importance sampling, whereby informative data points are sampled more…

Cryptography and Security · Computer Science 2025-03-31 Dominik Fay , Sebastian Mair , Jens Sjölund

A large body of research has shown that machine learning models are vulnerable to membership inference (MI) attacks that violate the privacy of the participants in the training data. Most MI research focuses on the case of a single…

Machine Learning · Computer Science 2022-05-16 Matthew Jagielski , Stanley Wu , Alina Oprea , Jonathan Ullman , Roxana Geambasu