English
Related papers

Related papers: Revisiting Model-Agnostic Private Learning: Faster…

200 papers

The rapid adoption of machine learning has increased concerns about the privacy implications of machine learning models trained on sensitive data, such as medical records or other personal information. To address those concerns, one…

Machine Learning · Statistics 2018-02-27 Nicolas Papernot , Shuang Song , Ilya Mironov , Ananth Raghunathan , Kunal Talwar , Úlfar Erlingsson

The Private Aggregation of Teacher Ensembles (PATE) is an important private machine learning framework. It combines multiple learning models used as teachers for a student model that learns to predict an output chosen by noisy voting among…

Machine Learning · Computer Science 2021-09-20 Cuong Tran , My H. Dinh , Kyle Beiter , Ferdinando Fioretto

Some machine learning applications involve training data that is sensitive, such as the medical histories of patients in a clinical trial. A model may inadvertently and implicitly store some of its training data; careful analysis of the…

Machine Learning · Statistics 2017-03-06 Nicolas Papernot , Martín Abadi , Úlfar Erlingsson , Ian Goodfellow , Kunal Talwar

Deep learning models trained on large-scale data have achieved encouraging performance in many real-world tasks. Meanwhile, publishing those models trained on sensitive datasets, such as medical records, could pose serious privacy concerns.…

Machine Learning · Computer Science 2022-11-04 Qiuchen Zhang , Jing Ma , Jian Lou , Li Xiong , Xiaoqian Jiang

When learning from sensitive data, care must be taken to ensure that training algorithms address privacy concerns. The canonical Private Aggregation of Teacher Ensembles, or PATE, computes output labels by aggregating the predictions of a…

Machine Learning · Computer Science 2022-09-23 Jiaqi Wang , Roei Schuster , Ilia Shumailov , David Lie , Nicolas Papernot

Differential privacy (DP) is one data protection avenue to safeguard user information used for training deep models by imposing noisy distortion on privacy data. Such a noise perturbation often results in a severe performance degradation in…

The Private Aggregation of Teacher Ensembles (PATE) framework enables privacy-preserving machine learning by aggregating responses from disjoint subsets of sensitive data. Adaptations of PATE to tasks with inherent output diversity such as…

Machine Learning · Computer Science 2025-10-02 Edith Cohen , Benjamin Cohen-Wang , Xin Lyu , Jelani Nelson , Tamas Sarlos , Uri Stemmer

The utility of machine learning has rapidly expanded in the last two decades and presents an ethical challenge. Papernot et. al. developed a technique, known as Private Aggregation of Teacher Ensembles (PATE) to enable federated learning in…

A critical concern in data-driven processes is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the group…

Machine Learning · Computer Science 2022-04-12 Cuong Tran , Keyu Zhu , Ferdinando Fioretto , Pascal Van Hentenryck

We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech applications. The AAE…

Sound · Computer Science 2021-10-11 Chao-Han Huck Yang , Sabato Marco Siniscalchi , Chin-Hui Lee

When it comes to preserving privacy in medical machine learning, two important considerations are (1) keeping data local to the institution and (2) avoiding inference of sensitive information from the trained model. These are often…

Computer Vision and Pattern Recognition · Computer Science 2020-04-15 Dominik Fay , Jens Sjölund , Tobias J. Oechtering

Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information. Most privacy-preserving methods lead to undesirable performance…

Cryptography and Security · Computer Science 2019-09-19 Lichao Sun , Yingbo Zhou , Ji Wang , Jia Li , Richard Sochar , Philip S. Yu , Caiming Xiong

We study the rates of convergence in generalization error achievable by active learning under various types of label noise. Additionally, we study the general problem of model selection for active learning with a nested hierarchy of…

Statistics Theory · Mathematics 2011-03-10 Steve Hanneke

Generating high-fidelity synthetic tabular data under formal differential privacy guarantees remains an open challenge. Methods that provide strong theoretical protection typically sacrifice the modeling of inter-feature dependencies…

Machine Learning · Computer Science 2026-05-27 M. Youssef , M. Woźniak

Deep learning-based language models have achieved state-of-the-art results in a number of applications including sentiment analysis, topic labelling, intent classification and others. Obtaining text representations or embeddings using these…

Computation and Language · Computer Science 2021-08-30 Richard Plant , Dimitra Gkatzia , Valerio Giuffrida

Applying machine learning (ML) to sensitive domains requires privacy protection of the underlying training data through formal privacy frameworks, such as differential privacy (DP). Yet, usually, the privacy of the training data comes at…

Machine Learning · Computer Science 2022-11-09 Franziska Boenisch , Christopher Mühl , Roy Rinberg , Jannis Ihrig , Adam Dziedzic

We provide an end-to-end Renyi DP based-framework for differentially private top-$k$ selection. Unlike previous approaches, which require a data-independent choice on $k$, we propose to privately release a data-dependent choice of $k$ such…

Machine Learning · Computer Science 2022-03-31 Yuqing Zhu , Yu-Xiang Wang

We introduce a simple framework for designing private boosting algorithms. We give natural conditions under which these algorithms are differentially private, efficient, and noise-tolerant PAC learners. To demonstrate our framework, we use…

Machine Learning · Computer Science 2020-02-05 Mark Bun , Marco Leandro Carmosino , Jessica Sorrell

Active learning refers to the learning protocol where the learner is allowed to choose a subset of instances for labeling. Previous studies have shown that, compared with passive learning, active learning is able to reduce the label…

Machine Learning · Computer Science 2014-02-07 Lijun Zhang , Mehrdad Mahdavi , Rong Jin

We present a simple noise-robust margin-based active learning algorithm to find homogeneous (passing the origin) linear separators and analyze its error convergence when labels are corrupted by noise. We show that when the imposed noise…

Machine Learning · Statistics 2015-11-25 Yining Wang , Aarti Singh
‹ Prev 1 2 3 10 Next ›