Search

Your search keyword '"Ralf Küsters"' showing total 205 results
Start Over Author "Ralf Küsters"
205 results on '"Ralf Küsters"'

13. Intelligent Methods for Test and Reliability.

Author

Hussam Amrouch, Jens Anders, Steffen Becker 0001, Maik Betka, Gerd Bleher, Peter Domanski, Nourhan Elhamawy, Thomas Ertl, Athanasios Gatzastras, Paul R. Genssler, Sebastian Hasler, Martin Heinrich, André van Hoorn, Hanieh Jafarzadeh, Ingmar Kallfass, Florian Klemme, Steffen Koch 0001, Ralf Küsters, Andrés Lalama, Raphaël Latty, Yiwen Liao, Natalia Lylina, Zahra Paria Najafi-Haghi, Dirk Pflüger, Ilia Polian, Jochen Rivoir, Matthias Sauer 0002, Denis Schwachhofer, Steffen Templin, Christian Volmer, Stefan Wagner 0001, Daniel Weiskopf, Hans-Joachim Wunderlich, Bin Yang 0009, and Martin Zimmermann

Published
2022
Full Text
View/download PDF

24. Convolutions in Overdrive: Maliciously Secure Convolutions for MPC

Author

Marc Rivinius, Pascal Reisert, Sebastian Hasler, and Ralf Küsters

Subjects
General Earth and Planetary Sciences, General Environmental Science
Abstract

Machine learning (ML) has seen a strong rise in popularity in recent years and has become an essential tool for research and industrial applications. Given the large amount of high quality data needed and the often sensitive nature of ML data, privacy-preserving collaborative ML is of increasing importance. In this paper, we introduce new actively secure multiparty computation (MPC) protocols which are specially optimized for privacy-preserving machine learning applications. We concentrate on the optimization of (tensor) convolutions which belong to the most commonly used components in ML architectures, especially in convolutional neural networks but also in recurrent neural networks or transformers, and therefore have a major impact on the overall performance. Our approach is based on a generalized form of structured randomness that speeds up convolutions in a fast online phase. The structured randomness is generated with homomorphic encryption using adapted and newly constructed packing methods for convolutions, which might be of independent interest. Overall our protocols extend the state-of-the-art Overdrive family of protocols (Keller et al., EUROCRYPT 2018). We implemented our protocols on-top of MP-SPDZ (Keller, CCS 2020) resulting in a full-featured implementation with support for faster convolutions. Our evaluation shows that our protocols outperform state-of-the-art actively secure MPC protocols on ML tasks like evaluating ResNet50 by a factor of 3 or more. Benchmarks for depthwise convolutions show order-of-magnitude speed-ups compared to existing approaches.

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results