A Privacy-Preserving Distributed Architecture for Deep-Learning-as-a-Service

Disabato, Simone; Falcetta, Alessandro; Mongelluzzo, Alessio; Roveri, Manuel

doi:10.1109/ijcnn48605.2020.9207619

Cited by 12 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Disabato et al [48] proposed an innovative distributed design for Deep Learning as a Service (DLaaS) which protects customers' sensitive data while offering cloudbased DL services. The suggested architecture is executed using a client server RESTbased framework for sharing encrypted data and findings among both client and server.…”

Section: Private Inferencingmentioning

confidence: 99%

Secure Data Computation Using Deep Learning and Homomorphic Encryption: A Survey

Al-Janabi

Al‐Khateeb

2023

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Deep learning and its variant techniques have surpassed classical machine algorithms due to their high performance gaining remarkable results and are used in a broad range of applications. However, adopting deep learning models over the cloud introduces privacy and security issues for data owners and model owners, including computational inefficiency, expansion in ciphertext, error accumulation, security and usability trade-offs, and deep learning model attacks. With homomorphic encryption, computations on encrypted data can be performed without disclosing its content. This research examines the basic concepts of homomorphic encryption limitations, benefits, weaknesses, possible applications, and development tools concentrating on neural networks. Additionally, we looked at systems that integrate neural networks with homomorphic encryption in order to maintain privacy. Furthermore, we classify modifications made on neural network models and architectures that make them computable via homomorphic encryption and the effect of these changes on performance. This paper introduces a thorough review focusing on the privacy of homomorphic cryptosystems targeting neural network models and identifies existing solutions, analyzes potential weaknesses, and makes recommendations for further research.

show abstract

Section: Private Inferencingmentioning

confidence: 99%

Secure Data Computation Using Deep Learning and Homomorphic Encryption: A Survey

Al-Janabi

Al‐Khateeb

2023

Int. J. Onl. Eng.

View full text Add to dashboard Cite

show abstract

“…The encryption process in the BFV scheme involves transforming plaintext data into ciphertext using a public key [56]. The computations can be directly conducted on the ciphertext, preserving the confidentiality of the underlying plaintext [57]. The BFV scheme supports various mathematical operations on encrypted data, such as addition and multiplication.…”

Section: He Parameters and Pyfhelmentioning

confidence: 99%

A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks

Nikfam,

Casaburi,

Marchisio

et al. 2023

Information

View full text Add to dashboard Cite

Machine learning (ML) is widely used today, especially through deep neural networks (DNNs); however, increasing computational load and resource requirements have led to cloud-based solutions. To address this problem, a new generation of networks has emerged called spiking neural networks (SNNs), which mimic the behavior of the human brain to improve efficiency and reduce energy consumption. These networks often process large amounts of sensitive information, such as confidential data, and thus privacy issues arise. Homomorphic encryption (HE) offers a solution, allowing calculations to be performed on encrypted data without decrypting them. This research compares traditional DNNs and SNNs using the Brakerski/Fan-Vercauteren (BFV) encryption scheme. The LeNet-5 and AlexNet models, widely-used convolutional architectures, are used for both DNN and SNN models based on their respective architectures, and the networks are trained and compared using the FashionMNIST dataset. The results show that SNNs using HE achieve up to 40% higher accuracy than DNNs for low values of the plaintext modulus t, although their execution time is longer due to their time-coding nature with multiple time steps.

show abstract

“…Concrete [31] is a Rust implementation of the TFHE scheme, while a few examples of software libraries specifically intended for HE-based machine and deep learning are available, such as PyCrCNN [32], nGraph-HE [9], and CHET [33].…”

Section: Available Resources For Privacy-preserving Deep Learning Wit...mentioning

confidence: 99%

Privacy-Preserving Deep Learning With Homomorphic Encryption: An Introduction

Falcetta

Roveri

2022

IEEE Comput. Intell. Mag.

Self Cite

View full text Add to dashboard Cite

Privacy-preserving deep learning with homomorphic encryption (HE) is a novel and promising research area aimed at designing deep learning solutions that operate while guaranteeing the privacy of user data. Designing privacypreserving deep learning solutions requires one to completely rethink and redesign deep learning models and algorithms to match the severe technological and algorithmic constraints of HE. This paper provides an introduction to this complex research area as well as a methodology for designing privacy-preserving convolutional neural networks (CNNs). This methodology was applied to the design of a privacy-preserving version of the well-known LeNet-1 CNN, which was successfully operated on two benchmark datasets for image classification. Furthermore, this paper details and comments on the research challenges and software resources available for privacy-preserving deep learning with HE.

show abstract

A Privacy-Preserving Distributed Architecture for Deep-Learning-as-a-Service

Cited by 12 publications

References 19 publications

Secure Data Computation Using Deep Learning and Homomorphic Encryption: A Survey

Secure Data Computation Using Deep Learning and Homomorphic Encryption: A Survey

A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks

Privacy-Preserving Deep Learning With Homomorphic Encryption: An Introduction

Contact Info

Product

Resources

About