English
Related papers

Related papers: Epsilon*: Privacy Metric for Machine Learning Mode…

200 papers

Machine unlearning, an emerging research topic focusing on compliance with data privacy regulations, enables trained models to remove the information learned from specific data. While many existing methods indirectly address this issue by…

Machine Learning · Computer Science 2024-12-24 Seonguk Seo , Dongwan Kim , Bohyung Han

As in traditional machine learning models, models trained with federated learning may exhibit disparate performance across demographic groups. Model holders must identify these disparities to mitigate undue harm to the groups. However,…

Machine Learning · Computer Science 2023-01-12 Marc Juarez , Aleksandra Korolova

The integration of machine learning (ML) in numerous critical applications introduces a range of privacy concerns for individuals who provide their datasets for model training. One such privacy risk is Membership Inference (MI), in which an…

Machine Learning · Computer Science 2024-01-18 Harsh Chaudhari , Giorgio Severi , Alina Oprea , Jonathan Ullman

Generative models producing synthetic data are meant to provide a privacy-friendly approach to releasing data. However, their privacy guarantees are only considered robust when models satisfy Differential Privacy (DP). Alas, this is not a…

Cryptography and Security · Computer Science 2025-05-09 Georgi Ganev , Emiliano De Cristofaro

Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include components for training data filtering, output monitoring,…

Artificial intelligence systems are prevalent in everyday life, with use cases in retail, manufacturing, health, and many other fields. With the rise in AI adoption, associated risks have been identified, including privacy risks to the…

Machine Learning · Computer Science 2024-07-19 Shlomit Shachor , Natalia Razinkov , Abigail Goldsteen

Designing privacy-preserving machine learning algorithms has received great attention in recent years, especially in the setting when the data contains sensitive information. Differential privacy (DP) is a widely used mechanism for data…

Machine Learning · Computer Science 2025-09-11 Chunyang Liao , Deanna Needell , Hayden Schaeffer , Alexander Xue

Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving…

Machine Learning · Computer Science 2011-02-18 Kamalika Chaudhuri , Claire Monteleoni , Anand D. Sarwate

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Cryptography and Security · Computer Science 2024-04-02 Shanglun Feng , Florian Tramèr

In statistical disclosure control, the goal of data analysis is twofold: The released information must provide accurate and useful statistics about the underlying population of interest, while minimizing the potential for an individual…

Methodology · Statistics 2016-07-15 Jing Lei , Anne-Sophie Charest , Aleksandra Slavkovic , Adam Smith , Stephen Fienberg

In this note, we consider the problem of differentially privately (DP) computing an anonymized histogram, which is defined as the multiset of counts of the input dataset (without bucket labels). In the low-privacy regime $\epsilon \geq 1$,…

Data Structures and Algorithms · Computer Science 2021-11-08 Pasin Manurangsi

Model Inversion attacks aim to reconstruct information from private training data by exploiting access to a target model. Nearly all recent MI studies evaluate attack success using a standard framework that computes attack accuracy through…

Machine Learning · Computer Science 2026-05-15 Sy-Tuyen Ho , Koh Jun Hao , Ngoc-Bao Nguyen , Alexander Binder , Ngai-Man Cheung

While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference, where an adversary…

Cryptography and Security · Computer Science 2020-09-11 Yang Zou , Zhikun Zhang , Michael Backes , Yang Zhang

This paper introduces a paradigm shift in the way privacy is defined, driven by a novel interpretation of the fundamental result of Dwork and Naor about the impossibility of absolute disclosure prevention. We propose a general model of…

Cryptography and Security · Computer Science 2024-10-28 Sara Saeidian , Giulia Cervia , Tobias J. Oechtering , Mikael Skoglund

We consider the problem of fitting a linear model to data held by individuals who are concerned about their privacy. Incentivizing most players to truthfully report their data to the analyst constrains our design to mechanisms that provide…

Computer Science and Game Theory · Computer Science 2015-06-12 Rachel Cummings , Stratis Ioannidis , Katrina Ligett

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

Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such…

Machine Learning · Computer Science 2020-07-20 Shruti Tople , Amit Sharma , Aditya Nori

The worldwide adoption of machine learning (ML) and deep learning models, particularly in critical sectors, such as healthcare and finance, presents substantial challenges in maintaining individual privacy and fairness. These two elements…

Machine Learning · Computer Science 2024-04-16 Mengmeng Yang , Ming Ding , Youyang Qu , Wei Ni , David Smith , Thierry Rakotoarivelo

Label differential privacy (label-DP) is a popular framework for training private ML models on datasets with public features and sensitive private labels. Despite its rigorous privacy guarantee, it has been observed that in practice…

Machine Learning · Computer Science 2023-06-06 Ruihan Wu , Jin Peng Zhou , Kilian Q. Weinberger , Chuan Guo

Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only…

Cryptography and Security · Computer Science 2023-10-19 Yixin Wu , Rui Wen , Michael Backes , Pascal Berrang , Mathias Humbert , Yun Shen , Yang Zhang