Practical Secure Aggregation for Privacy-Preserving Machine Learning

Bonawitz, Keith; Ivanov, Vladimir; Kreuter, Ben; Marcedone, Antonio; McMahan, H. Brendan; Patel, Sarvar; Ramage, Daniel; Segal, Aaron; Seth, Karn

doi:10.1145/3133956.3133982

Cited by 2,377 publications

(1,928 citation statements)

References 34 publications

Supporting

Mentioning

1,721

Contrasting

Unclassified

Order By: Relevance

“…On the other hand, from a technical point of view, how to store, query, and process data such that there is no privacy concerns for building deep learning systems has now become an even more difficult but interesting challenge. Building a privacy-preserving algorithm requires to combine cryptography and deep learning together and to mix techniques from a wide range of subjects such as data analysis, distributed computing, federated learning, differential privacy, in order to achieve models with strong security, fast run time, and great generalizability (Dwork and Roth, 2014;Abadi et al, 2016;Bonawitz et al, 2017;Ryffel et al, 2018). In this respect, Papernot (2018) published a report for guidance, which summarized a set of best practices for improving the privacy and security of machine learning systems.…”

Section: Future Workmentioning

confidence: 99%

Deep Learning for Cardiac Image Segmentation: A Review

Chen

Qiu

et al. 2020

Front. Cardiovasc. Med.

648

383

View full text Add to dashboard Cite

Deep learning has become the most widely used approach for cardiac image segmentation in recent years. In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound (US) and major anatomical structures of interest (ventricles, atria and vessels). In addition, a summary of publicly available cardiac image datasets and code repositories are included to provide a base for encouraging reproducible research. Finally, we discuss the challenges and limitations with current deep learning-based approaches (scarcity of labels, model generalizability across different domains, interpretability) and suggest potential directions for future research.

show abstract

Section: Future Workmentioning

confidence: 99%

Deep Learning for Cardiac Image Segmentation: A Review

Chen

Qiu

et al. 2020

Front. Cardiovasc. Med.

648

383

View full text Add to dashboard Cite

show abstract

“…In a world permeated by smart devices with tremendous computing power and ubiquitous network access, such an approach could soon be poised to combine the above ideas into a powerful global knowledge extraction "organism", which is the underlying idea of Google's new federated learning approach [85]. In a recent work they trained a deep neural network (for an overview of deep learning in neural networks refer to: [3]) in a federated learning model by application of distributed gradient descent across user-held training data on mobile devices [86], which is a current hot topic [87].…”

Section: Knowledge Extraction (Ke)mentioning

confidence: 99%

Introduction to MAchine Learning & Knowledge Extraction (MAKE)

Holzinger¹

2017

MAKE

View full text Add to dashboard Cite

Abstract:The grand goal of Machine Learning is to develop software which can learn from previous experience-similar to how we humans do. Ultimately, to reach a level of usable intelligence, we need (1) to learn from prior data, (2) to extract knowledge, (3) to generalize-i.e., guessing where probability function mass/density concentrates, (4) to fight the curse of dimensionality, and (5) to disentangle underlying explanatory factors of the data-i.e., to make sense of the data in the context of an application domain. To address these challenges and to ensure successful machine learning applications in various domains an integrated machine learning approach is important. This requires a concerted international effort without boundaries, supporting collaborative, cross-domain, interdisciplinary and transdisciplinary work of experts from seven sections, ranging from data pre-processing to data visualization, i.e., to map results found in arbitrarily high dimensional spaces into the lower dimensions to make it accessible, usable and useful to the end user.

show abstract

“…Bonawitz et al demonstrate SECAGG, a practical protocol for secure aggregation in the federated learning setting, achieving < 2× communication expansion while tolerating up to 1 3 user devices dropping out midway through the protocol and while maintaining security against an adversary with malicious control of up to 1 3 of the user devices and full visibility of everything happening on the server [6]. The key idea in SECAGG is to have each pair of users agree on randomly sampled 0-sum pairs of mask vectors of the same lengths as the model updates.…”

Section: B Secure Aggregationmentioning

confidence: 99%

Federated Learning with Autotuned Communication-Efficient Secure Aggregation

Bonawitz

Salehi

Konečný

et al. 2019

2019 53rd Asilomar Conference on Signals, Systems, and Computers

Self Cite

124

View full text Add to dashboard Cite

Federated Learning enables mobile devices to collaboratively learn a shared inference model while keeping all the training data on a user's device, decoupling the ability to do machine learning from the need to store the data in the cloud. Existing work on federated learning with limited communication demonstrates how random rotation can enable users' model updates to be quantized much more efficiently, reducing the communication cost between users and the server. Meanwhile, secure aggregation enables the server to learn an aggregate of at least a threshold number of device's model contributions without observing any individual device's contribution in unaggregated form. In this paper, we highlight some of the challenges of setting the parameters for secure aggregation to achieve communication efficiency, especially in the context of the aggressively quantized inputs enabled by random rotation. We then develop a recipe for auto-tuning communication-efficient secure aggregation, based on specific properties of random rotation and secure aggregation -namely, the predictable distribution of vector entries postrotation and the modular wrapping inherent in secure aggregation. We present both theoretical results and initial experiments.

show abstract

Practical Secure Aggregation for Privacy-Preserving Machine Learning

Cited by 2,377 publications

References 34 publications

Deep Learning for Cardiac Image Segmentation: A Review

Deep Learning for Cardiac Image Segmentation: A Review

Introduction to MAchine Learning & Knowledge Extraction (MAKE)

Federated Learning with Autotuned Communication-Efficient Secure Aggregation

Contact Info

Product

Resources

About