CRLGJul 9, 2019

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

arXiv:1907.04246v11 citations
Originality Synthesis-oriented
AI Analysis

This addresses security concerns for enterprises deploying AI at the edge, but it is incremental as it applies existing encryption methods to a new context.

The paper tackles the problem of securing distributed deep neural networks by proposing a holistic approach using Fully Homomorphic Encryption to protect data confidentiality and intellectual property, and evaluates its feasibility on a CNN for image classification in distributed infrastructures.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes