FHE is a powerful cryptographic primitive that enables performing computations over encrypted data without having to decrypt any data or share access to any secret keys. FHE covers a set of encryption methodologies that allow computations to be performed on encrypted data while it is being used – without ever decrypting it. FHE schemes use a mapping between two mathematical structures that preserves the computational characteristics of the structures. This allows operations to be run directly on encrypted data (ciphertexts), while yielding the same results as if the functions were run on plaintext.
Duality is a prime contributor to the research and development of OpenFHE, an open-source privacy-preserving cryptography library, which is designed for usability and performance, providing simpler APIs, modularity, cross-platform support, and integration of hardware accelerators. OpenFHE complies with the HomomorphicEncryption.org post-quantum security standards for homomorphic encryption. For more info regarding OpenFHE, visit https://www.openfhe.org/.
Multi-party computation, commonly referred as MPC, is a PET technique that utilizes cryptography techniques to allow multiple parties to perform joint computations on individual inputs without revealing the underlying data between them or interim computations.
Secure Federated Learning
Federated Learning (FL) is a distributed machine learning (ML) technique that enables model training on data from multiple, decentralized servers with local data samples, without exchanging or moving data. This approach ensures that the data remains in its original location and is not exposed to any other parties.
Another characteristic of FL is that it is typically composed of heterogeneous datasets where the size of the dataset varies from one data owner to another.
Duality developed a second layer of security on top of FL to ensure that the federated computation itself is performed while encrypted, keeping the model concealed from all participants and the computation operation secured.
Trusted Execution Environment
Trusted Execution Environments (TEEs) provide secure computation capability through a combination of special-purpose hardware and software built to use those hardware features. It provides a mechanism by which a process can run on a processor without its memory or execution state being visible to any other process on the processor, even the operating system or other privileged code.
Other processes (whether local or remote) that must trust an enclave can receive attestation that the enclave is genuine, and that the code running in it and the static parts of its memory space are exactly what is expected. Such attestation is guaranteed using cryptographic capabilities. Duality added the option to use TEE that works in conjunction with the cryptographic solutions. The platform runs on top of AWS nitro enclave and Google confidential space. Azure TEE is in the roadmap.