SoK: Cryptography for Neural Networks

Autor: Eleonora Ciceri, Sauro Vicini, Monir Azraoui, Orhan Ermis, Marie Paindavoine, Sébastien Canard, Ramy Masalha, Muhammad Bahram, Melek Önen, Beyza Bozdemir, Bastien Vialla, Boris Rozenberg, Marco Mosconi
Přispěvatelé: Eurecom [Sophia Antipolis], IBM Haifa Research Lab (IBM HRL), IBM R&D Labs in Israel, Orange Labs [Caen], Orange Labs, ANR-19-P3IA-0002,3IA@cote d'azur,3IA Côte d'Azur(2019)
Jazyk: angličtina
Rok vydání: 2019
Předmět:
Zdroj: Privacy and Identity Management. Data for Better Living: AI and Privacy 14th IFIP WG 9.2, 9.6/11.7, 11.6/SIG 9.2.2 International Summer School, Windisch, Switzerland, August 19–23, 2019, Revised Selected Papers
IFIP 2019, IFIP Summer School on Privacy and Identity Management
IFIP 2019, IFIP Summer School on Privacy and Identity Management, Aug 2019, Brugg Windisch, Switzerland. ⟨10.1007/978-3-030-42504-3_5⟩
Privacy and Identity Management. Data for Better Living: AI and Privacy ISBN: 9783030425036
Privacy and Identity Management
Privacy and Identity Management. Data for Better Living: AI and Privacy-14th IFIP WG 9.2, 9.6/11.7, 11.6/SIG 9.2.2 International Summer School, Windisch, Switzerland, August 19–23, 2019, Revised Selected Papers
DOI: 10.1007/978-3-030-42504-3_5⟩
Popis: International audience; With the advent of big data technologies which bring better scalability and performance results, machine learning (ML) algorithms become affordable in several different applications and areas. The use of large volumes of data to obtain accurate predictions unfortunately come with a high cost in terms of privacy exposures. The underlying data are often personal or confidential and, therefore, need to be appropriately safeguarded. Given the cost of machine learning algorithms, these would need to be outsourced to third-party servers, and hence protection of the data becomes mandatory. While traditional data encryption solutions would not allow accessing the content of the data, these would, nevertheless, prevent third-party servers from executing the ML algorithms properly. The goal is, therefore, to come up with customized ML algorithms that would, by design, preserve the privacy of the processed data. Advanced cryptographic techniques such as fully homomorphic encryption or secure multi-party computation enable the execution of some operations over protected data and, therefore, can be considered as potential candidates for these algorithms. However, these techniques incur high computational and/or communication costs for some operations. In this paper, we propose a Systematization of Knowledge (SoK) whereby we analyze the tension between a particular ML technique, namely, neural networks (NN), and the characteristics of relevant cryptographic techniques.
Databáze: OpenAIRE
Externí odkaz: