English
Related papers

Related papers: A Bayesian Approach to Membership Inference for St…

200 papers

Membership Inference Attacks (MIAs) aim to estimate whether a specific data point was used in the training of a given model. Existing state-of-the-art attacks typically rely on training multiple reference models to approximate the…

Machine Learning · Computer Science 2026-05-26 Zhenlong Liu , Wenyu Jiang , Feng Zhou , Hongxin Wei

The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs leak information…

Machine Learning · Computer Science 2022-11-07 Fatemehsadat Mireshghallah , Kartik Goyal , Archit Uniyal , Taylor Berg-Kirkpatrick , Reza Shokri

In cognitive radio (CR) technology, the trend of sensing is no longer to only detect the presence of active primary users. A large number of applications demand for more comprehensive knowledge on primary user behaviors in spatial,…

Machine Learning · Computer Science 2015-02-10 Weijia Han , Huiyan Sang , Min Sheng , Jiandong Li , Shuguang Cui

We consider the problem of designing a survey to aggregate non-verifiable information from a privacy-sensitive population: an analyst wants to compute some aggregate statistic from the private bits held by each member of a population, but…

Computer Science and Game Theory · Computer Science 2014-04-25 Arpita Ghosh , Katrina Ligett , Aaron Roth , Grant Schoenebeck

Empirical inference attacks are a popular approach for evaluating the privacy risk of data release mechanisms in practice. While an active attack literature exists to evaluate machine learning models or synthetic data release, we currently…

Cryptography and Security · Computer Science 2025-04-28 Yifeng Mao , Bozhidar Stevanoski , Yves-Alexandre de Montjoye

Generative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data…

Cryptography and Security · Computer Science 2018-08-22 Jamie Hayes , Luca Melis , George Danezis , Emiliano De Cristofaro

Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditing tool for measuring privacy leakage from sensitive…

Machine Learning · Computer Science 2020-09-21 Abhinav Aggarwal , Zekun Xu , Oluwaseyi Feyisetan , Nathanael Teissier

Membership inference determines, given a sample and trained parameters of a machine learning model, whether the sample was part of the training set. In this paper, we derive the optimal strategy for membership inference with a few…

Machine Learning · Statistics 2019-08-30 Alexandre Sablayrolles , Matthijs Douze , Yann Ollivier , Cordelia Schmid , Hervé Jégou

Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we…

Cryptography and Security · Computer Science 2022-12-05 Tomas Chobola , Dmitrii Usynin , Georgios Kaissis

When releasing outputs from confidential data, agencies need to balance the analytical usefulness of the released data with the obligation to protect data subjects' confidentiality. For releases satisfying differential privacy, this balance…

Cryptography and Security · Computer Science 2024-05-24 Zeki Kazan , Jerome P. Reiter

Recently, recommender systems have achieved promising performances and become one of the most widely used web applications. However, recommender systems are often trained on highly sensitive user data, thus potential data leakage from…

Cryptography and Security · Computer Science 2021-09-17 Minxing Zhang , Zhaochun Ren , Zihan Wang , Pengjie Ren , Zhumin Chen , Pengfei Hu , Yang Zhang

The tension between persuasion and privacy preservation is common in real-world settings. Online platforms should protect the privacy of web users whose data they collect, even as they seek to disclose information about these data to…

Computer Science and Game Theory · Computer Science 2024-02-27 Yuqi Pan , Zhiwei Steven Wu , Haifeng Xu , Shuran Zheng

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

Machine Learning · Computer Science 2022-09-14 Jiayuan Ye , Aadyaa Maddi , Sasi Kumar Murakonda , Vincent Bindschaedler , Reza Shokri

Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most existing research focuses primarily on balancing the sparsity and…

Cryptography and Security · Computer Science 2022-08-05 Xiaoyong Yuan , Lan Zhang

Three different inferential problems related to a two dimensional categorical data from a Bayesian perspective have been discussed in this article. Conjugate prior distribution with symmetric and asymmetric hyper parameters are considered.…

Statistics Theory · Mathematics 2024-09-05 Samyajoy Pal , Christian Heumann , M. Subbiah

We propose a general statistical inference framework to capture the privacy threat incurred by a user that releases data to a passive but curious adversary, given utility constraints. We show that applying this general framework to the…

Information Theory · Computer Science 2012-10-09 Flavio du Pin Calmon , Nadia Fawaz

We propose Bayesian methods to assess the statistical disclosure risk of data released under zero-concentrated differential privacy, focusing on settings with a strong hierarchical structure and categorical variables with many levels. Risk…

Methodology · Statistics 2023-02-01 Zeki Kazan , Jerome Reiter

Membership inference attack (MIA) has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. These attacks aim to determine whether a specific sample is part of the model's…

Cryptography and Security · Computer Science 2025-06-04 Jing Xue , Zhishen Sun , Haishan Ye , Luo Luo , Xiangyu Chang , Ivor Tsang , Guang Dai

We study probabilistic safety for Bayesian Neural Networks (BNNs) under adversarial input perturbations. Given a compact set of input points, $T \subseteq \mathbb{R}^m$, we study the probability w.r.t. the BNN posterior that all the points…

Machine Learning · Computer Science 2020-06-22 Matthew Wicker , Luca Laurenti , Andrea Patane , Marta Kwiatkowska

Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service API. In providing an in-depth characterization of…

Cryptography and Security · Computer Science 2019-02-04 Stacey Truex , Ling Liu , Mehmet Emre Gursoy , Lei Yu , Wenqi Wei