News for hackers. Stuff that matters.

xsamgreen

Re:Intel to Build Silicon for Fully Homomorphic Encryption on Tuesday March 09, 2021 @01:01PM (#26401523)
Definitely agreed that CPU is a natural baseline. But there are promising results for implementing NTT on GPUs. Here is something recent https://eprint.iacr.org/2021/124

Nothing will beat an ASIC for NTT though.

Re:Intel to Build Silicon for Fully Homomorphic Encryption on Tuesday March 09, 2021 @12:57PM (#26401486)
Remote clients are the only ones with the encryption/decryption keys. The compute provider (Intel in this case) only has public keys. If the remote client is using trusted open source software, I wish the compute provider the best of luck in extracting any information from what they are processing.
Re:Intel to Build Silicon for Fully Homomorphic Encryption on Tuesday March 09, 2021 @12:54PM (#26401443)
You may be thinking of Indistinguishability Obfuscation. Current FHE algorithms (e.g. those undergoing standardization: https://homomorphicencryption.org/) don't provide IO. The compute provider knows the exact graph that is being computed, but, in the most secure scenario, they don't get to know the inputs and outputs of each node in the graph. The node operation (which can be only addition or multiplication) must be known to the compute provider so they can perform the correct mathematical transforms on the encrypted data.
Re:Intel to Build Silicon for Fully Homomorphic Encryption on Tuesday March 09, 2021 @12:44PM (#26401319)
10^5 speed up will get them to 10x slower than plaintext processing of deep neural networks. See page 15 of DARPA's BAA:

https://beta.sam.gov/api/prod/opps/v3/opportunities/resource...

For simple computing like logistic regression, they aim to be as fast as plaintext.

FHE is undergoing standardization right now. The leading algorithm candidates are based on lattice crypto which is currently quantum-safe: https://homomorphicencryption.org/

Here are some mature and actively-developed HE libraries:

https://github.com/homenc/HElib (By IBM, employed the inventor of FHE)

https://github.com/Microsoft/SEAL (Best tutorials)

https://palisade-crypto.org/software-library (High-quality codebase)

https://github.com/tfhe/tfhe (Fast boolean logic, used by Cingulata)

Good introductory material is hard to come by, but I like the first half of this talk: https://simons.berkeley.edu/talks/intro-fhe-and-tfhe