Aarhus University Seal

On Fully Homomorphic Encryption for Privacy-Preserving Deep Learning

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

Given the rise of Machine Learning (ML) applications using sensitive private data, we present an implementation of Fully Homomorphic Encryption (FHE) with Convolutional Neural Networks (CNNs) for privacy-preserving Deep Learning (DL). This permits to utilize DL image recognition algorithms without compromising personal data of served customers, e.g medical images. The combination of FHE and CNN is accomplished by using logic circuits, which enable to conduct deep learning algorithms on ciphertext instead of plaintext. We provide a set of practical measurements from an implementation on the number of logic circuit operations required to carry out privacy-preserving ML. The results are function of the numerical representation and security parameters. Our results indicate that the protection of customer data is a trade-off between the required level of security, prediction capability and computational complexity. Thus, we reach full correct classification with 6 bits in the fractional part, and evaluate the time costs associated with our circuits as a function of its security parameters.

Original languageEnglish
Title of host publication2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings
Publication year13 Dec 2019
Article number9024625
ISBN (electronic)978-1-7281-0960-2
Publication statusPublished - 13 Dec 2019
Event2019 IEEE Global Communications Conference - Waikoloa, HI, USA, Waikoloa, United States
Duration: 9 Dec 201913 Dec 2019


Conference2019 IEEE Global Communications Conference
LocationWaikoloa, HI, USA
LandUnited States

    Research areas

  • Circuit Analysis, Convolutional Neural Network, Fully Homomorphic Encryption, Machine Learning, Privacy

See relations at Aarhus University Citationformats

ID: 215945245