English
Related papers

Related papers: Privacy Auditing with One (1) Training Run

200 papers

Differential privacy (DP) provides formal guarantees that the output of a database query does not reveal too much information about any individual present in the database. While many differentially private algorithms have been proposed in…

Cryptography and Security · Computer Science 2019-11-27 Royce J Wilson , Celia Yuxin Zhang , William Lam , Damien Desfontaines , Daniel Simmons-Marengo , Bryant Gipson

We address the problem of learning a machine learning model from training data that originates at multiple data owners while providing formal privacy guarantees regarding the protection of each owner's data. Existing solutions based on…

Cryptography and Security · Computer Science 2025-03-12 Sikha Pentyala , Davis Railsback , Ricardo Maia , Rafael Dowsley , David Melanson , Anderson Nascimento , Martine De Cock

Many applications of machine learning, for example in health care, would benefit from methods that can guarantee privacy of data subjects. Differential privacy (DP) has become established as a standard for protecting learning results. The…

Machine Learning · Statistics 2017-05-30 Mikko Heikkilä , Eemil Lagerspetz , Samuel Kaski , Kana Shimizu , Sasu Tarkoma , Antti Honkela

We study the privatization of distributed learning and optimization strategies. We focus on differential privacy schemes and study their effect on performance. We show that the popular additive random perturbation scheme degrades…

Machine Learning · Computer Science 2023-01-18 Elsa Rizk , Stefan Vlaski , Ali H. Sayed

Learning from continuous data streams via classification/regression is prevalent in many domains. Adapting to evolving data characteristics (concept drift) while protecting data owners' private information is an open challenge. We present a…

Machine Learning · Computer Science 2021-12-10 Lovedeep Gondara , Ke Wang , Ricardo Silva Carvalho

Data privacy is an important concern in machine learning, and is fundamentally at odds with the task of training useful learning models, which typically require the acquisition of large amounts of private user data. One possible way of…

Machine Learning · Computer Science 2019-02-14 Mehrdad Showkatbakhsh , Can Karakus , Suhas Diggavi

Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor…

Machine Learning · Computer Science 2026-05-22 Aman Saxena , Jan Schuchardt , Yan Scholten , Stephan Günnemann

Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack, he aims to…

Machine Learning · Statistics 2018-07-17 Milad Nasr , Reza Shokri , Amir Houmansadr

An important use of private data is to build machine learning classifiers. While there is a burgeoning literature on differentially private classification algorithms, we find that they are not practical in real applications due to two…

Machine Learning · Computer Science 2014-11-24 Ben Stoddard , Yan Chen , Ashwin Machanavajjhala

Fairness auditing of AI systems can identify and quantify biases. However, traditional auditing using real-world data raises security and privacy concerns. It exposes auditors to security risks as they become custodians of sensitive…

Computers and Society · Computer Science 2025-05-01 Chih-Cheng Rex Yuan , Bow-Yaw Wang

Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information instead of real data.…

Cryptography and Security · Computer Science 2021-05-24 Lichao Sun , Jianwei Qian , Xun Chen

Federated learning facilitates the collaborative training of models without the sharing of raw data. However, recent attacks demonstrate that simply maintaining data locality during training processes does not provide sufficient privacy…

Machine Learning · Computer Science 2019-08-16 Stacey Truex , Nathalie Baracaldo , Ali Anwar , Thomas Steinke , Heiko Ludwig , Rui Zhang , Yi Zhou

Through the lens of information-theoretic reductions, we examine a reductions approach to fair optimization and learning where a black-box optimizer is used to learn a fair model for classification or regression. Quantifying the complexity,…

Machine Learning · Computer Science 2021-05-25 Daniel Alabi

A centrally differentially private algorithm maps raw data to differentially private outputs. In contrast, a locally differentially private algorithm may only access data through public interaction with data holders, and this interaction…

Data Structures and Algorithms · Computer Science 2020-07-20 Kareem Amin , Matthew Joseph , Jieming Mao

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…

Machine Learning · Computer Science 2023-05-31 Stephan Rabanser , Anvith Thudi , Abhradeep Thakurta , Krishnamurthy Dvijotham , Nicolas Papernot

Strict privacy is of paramount importance in distributed machine learning. Federated learning, with the main idea of communicating only what is needed for learning, has been recently introduced as a general approach for distributed learning…

Cryptography and Security · Computer Science 2020-07-14 Mikko A. Heikkilä , Antti Koskela , Kana Shimizu , Samuel Kaski , Antti Honkela

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

Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data…

Cryptography and Security · Computer Science 2026-03-12 Francisco Aguilera-Martínez , Fernando Berzal

Machine learning models used for distributed architectures consisting of servers and clients require large amounts of data to achieve high accuracy. Data obtained from clients are collected on a central server for model training. However,…

Cryptography and Security · Computer Science 2025-09-18 Ozer Ozturk , Busra Buyuktanir , Gozde Karatas Baydogmus , Kazim Yildiz

Ratio statistics--such as relative risk and odds ratios--play a central role in hypothesis testing, model evaluation, and decision-making across many areas of machine learning, including causal inference and fairness analysis. However,…

Machine Learning · Statistics 2025-05-28 Tomer Shoham , Katrina Ligettt
‹ Prev 1 3 4 5 6 7 10 Next ›