English
Related papers

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

200 papers

Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model's accuracy.…

Machine Learning · Computer Science 2019-10-29 Eugene Bagdasaryan , Vitaly Shmatikov

Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy estimate (nearly)…

In this paper, we study the problem of privacy audit in one run and show that our method achieves tight audit results for various differentially private protocols. This includes obtaining tight results for auditing $(\varepsilon,\delta)$-DP…

Cryptography and Security · Computer Science 2025-09-11 Zihang Xiang , Tianhao Wang , Hanshen Xiao , Yuan Tian , Di Wang

In Embedding-as-an-Interface (EaaI) settings, pre-trained models are queried for Intermediate Representations (IRs). The distributional properties of IRs can leak training-set membership signals, enabling Membership Inference Attacks (MIAs)…

Machine Learning · Computer Science 2026-05-12 Jiayang Meng , Tao Huang , Chen Hou , Guolong Zheng , Hong Chen

Privacy estimation techniques for differentially private (DP) algorithms are useful for comparing against analytical bounds, or to empirically measure privacy loss in settings where known analytical bounds are not tight. However, existing…

Machine Learning · Computer Science 2024-04-19 Galen Andrew , Peter Kairouz , Sewoong Oh , Alina Oprea , H. Brendan McMahan , Vinith M. Suriyakumar

Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning. It provides a single privacy guarantee to all datapoints in the dataset. We propose output-specific…

Machine Learning · Computer Science 2024-07-26 Da Yu , Gautam Kamath , Janardhan Kulkarni , Tie-Yan Liu , Jian Yin , Huishuai Zhang

While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs). This paper presents an empirical evaluation of Differential Privacy (DP) as a defense…

Cryptography and Security · Computer Science 2026-04-16 Gustavo de Carvalho Bertoli

Differentially private stochastic gradient descent (DP-SGD) enables private deep learning through per-example clipping and calibrated Gaussian noise, but its high-variance updates can reduce utility on challenging datasets. We propose…

Machine Learning · Computer Science 2026-05-21 Mohammad Partohaghighi , Roummel Marcia

Privacy auditing provides empirical lower bounds on the differential privacy parameters of learning algorithms. Existing methods, however, require interventional access to the training pipeline, either to retrain multiple times or to…

Cryptography and Security · Computer Science 2026-05-15 Tudor Cebere , Mathieu Even , Linus Bleistein , Aurélien Bellet

Recent methods for auditing the privacy of machine learning algorithms have improved computational efficiency by simultaneously intervening on multiple training examples in a single training run. Steinke et al. (2024) prove that one-run…

Machine Learning · Computer Science 2026-02-23 Amit Keinan , Moshe Shenfeld , Katrina Ligett

Differentially private synthetic data generation (DP-SDG) algorithms are used to release datasets that are structurally and statistically similar to sensitive data while providing formal bounds on the information they leak. However, bugs in…

Cryptography and Security · Computer Science 2024-05-21 Meenatchi Sundaram Muthu Selva Annamalai , Georgi Ganev , Emiliano De Cristofaro

Machine learning models can be trained with formal privacy guarantees via differentially private optimizers such as DP-SGD. In this work, we focus on a threat model where the adversary has access only to the final model, with no visibility…

Machine Learning · Computer Science 2025-05-30 Tudor Cebere , Aurélien Bellet , Nicolas Papernot

Cognitive diagnosis models (CDMs) are pivotal for creating fine-grained learner profiles in modern intelligent education platforms. However, these models are trained on sensitive student data, raising significant privacy concerns. While…

Cryptography and Security · Computer Science 2025-11-10 Mingliang Hou , Yinuo Wang , Teng Guo , Zitao Liu , Wenzhou Dou , Jiaqi Zheng , Renqiang Luo , Mi Tian , Weiqi Luo

The remarkable proliferation of deep learning across various industries has underscored the importance of data privacy and security in AI pipelines. As the evolution of sophisticated Membership Inference Attacks (MIAs) threatens the secrecy…

Cryptography and Security · Computer Science 2023-06-06 Eugenio Lomurno , Alberto Archetti , Francesca Ausonio , Matteo Matteucci

We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward evaluating privacy loss through poisoning attacks or…

Machine Learning · Computer Science 2023-01-10 Fred Lu , Joseph Munoz , Maya Fuchs , Tyler LeBlond , Elliott Zaresky-Williams , Edward Raff , Francis Ferraro , Brian Testa

Given a trained model and a data sample, membership-inference (MI) attacks predict whether the sample was in the model's training set. A common countermeasure against MI attacks is to utilize differential privacy (DP) during model training…

Cryptography and Security · Computer Science 2022-04-14 Saeed Mahloujifar , Alexandre Sablayrolles , Graham Cormode , Somesh Jha

We study black-box auditing for machine learning algorithms that claim R \ 'enyi differential privacy (RDP) guarantees. We introduce an auditing framework, based on hypothesis testing, that directly estimates R\'enyi divergence between…

Machine Learning · Computer Science 2026-05-22 Benjamin D. Kim , Lav R. Varshney , Daniel Alabi

Traditionally, the random noise is equally injected when training with different data instances in the field of differential privacy (DP). In this paper, we first give sharper excess risk bounds of DP stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2023-01-31 Yilin Kang , Jian Li , Yong Liu , Weiping Wang

The increased application of machine learning (ML) in sensitive domains requires protecting the training data through privacy frameworks, such as differential privacy (DP). DP requires to specify a uniform privacy level $\varepsilon$ that…

Machine Learning · Computer Science 2024-01-31 Krishna Acharya , Franziska Boenisch , Rakshit Naidu , Juba Ziani

When training a machine learning model with differential privacy, one sets a privacy budget. This budget represents a maximal privacy violation that any user is willing to face by contributing their data to the training set. We argue that…

Machine Learning · Computer Science 2024-01-22 Franziska Boenisch , Christopher Mühl , Adam Dziedzic , Roy Rinberg , Nicolas Papernot