Security for Distributed Deep Neural Networks Towards Data Confidentiality & Intellectual Property Protection

by   Laurent Gomez, et al.

Current developments in Enterprise Systems observe a paradigm shift, moving the needle from the backend to the edge sectors of those; by distributing data, decentralizing applications and integrating novel components seamlessly to the central systems. Distributively deployed AI capabilities will thrust this transition. Several non-functional requirements arise along with these developments, security being at the center of the discussions. Bearing those requirements in mind, hereby we propose an approach to holistically protect distributed Deep Neural Network (DNN) based/enhanced software assets, i.e. confidentiality of their input & output data streams as well as safeguarding their Intellectual Property. Making use of Fully Homomorphic Encryption (FHE), our approach enables the protection of Distributed Neural Networks, while processing encrypted data. On that respect we evaluate the feasibility of this solution on a Convolutional Neuronal Network (CNN) for image classification deployed on distributed infrastructures.


page 1

page 2

page 3

page 4


On the Security of Pixel-Based Image Encryption for Privacy-Preserving Deep Neural Networks

This paper aims to evaluate the safety of a pixel-based image encryption...

How Secure is Distributed Convolutional Neural Network on IoT Edge Devices?

Convolutional Neural Networks (CNN) has found successful adoption in man...

Security Evaluation of Compressible Image Encryption for Privacy-Preserving Image Classification against Ciphertext-only Attacks

The security of learnable image encryption schemes for image classificat...

A feasibility study of deep neural networks for the recognition of banknotes regarding central bank requirements

This paper contains a feasibility study of deep neural networks for the ...

Learning-Based Data Storage [Vision] (Technical Report)

Deep neural network (DNN) and its variants have been extensively used fo...

Knowledge-Free Black-Box Watermark and Ownership Proof for Image Classification Neural Networks

Watermarking has become a plausible candidate for ownership verification...

Digital Passport: A Novel Technological Strategy for Intellectual Property Protection of Convolutional Neural Networks

In order to prevent deep neural networks from being infringed by unautho...