IBM HElayers#

IBM HElayers is a software development kit (SDK) for the practical and efficient execution of encrypted workloads using fully homomorphic encrypted data. HElayers is designed to enable application developers and data scientists to seamlessly apply advanced privacy-preserving techniques without requiring specialized skills in cryptography.

“HElayers experience survey”

Help us create the best possible offerings by providing feedback on how you use FHE. Take the HElayers experience survey.

Getting started#

Learn by experience

Users who are already familiar with the concepts of FHE, and who are eager to get started with HElayers, can easily install it and test the various tutorials and demos it provides.

Installation page

Learn by reading

Users who wish to learn more about the HElayers solution, its structure, its intended audience, and its different sets of APIs should visit its overview page.

Overview page

HElayers and IBM#

HElayers now powers IBM’s FHE Cloud Service, a beta cloud service that enables data scientists and developers to deploy privacy preserving machine learning driven Software-as-a-Service (SaaS) applications in the Cloud.
To learn more about our offerings for IBM zSystems, please visit our Content Solutions Page

License#

HElayers is provided under a community edition license for non-commercial use; see license. For commercial deployments and access to the source code, please contact chamliam@ie.ibm.com for the Premium Edition license.

Citing HElayers#

To cite HElayers, please use:

Aharoni, E., Adir, A., Baruch, M., Drucker, N., Ezov, G., Farkash, A., Greenberg, L., Masalha, R., Moshkowich, G., Murik, D., Shaul, H. and Soceanu, O., HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data, Privacy Enhancing Technology Symposium (PETs) 2023, https://petsymposium.org/popets/2023/popets-2023-0020.php

@article{helayers,
    author = {Aharoni, Ehud and Adir, Allon and Baruch, Moran and Drucker, Nir and Ezov, Gilad and Farkash, Ariel and Greenberg, Lev and Masalha, Ramy and Moshkowich, Guy and Murik, Dov and Shaul, Hayim and Soceanu, Omri},
    journal = {{Privacy Enhancing Technology Symposium (PETs) 2023}},
    title = {{HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data}},
    url = {https://petsymposium.org/popets/2023/popets-2023-0020.php},
    year = {2023},
    }