Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network — mentioned by mitchellpkt

Thu, 12 Jan 2023 18:33:26 GMT

Good questions. Hmm do you think maybe it would be viable if the payouts were based on [model] performance rather than ostensible training time? There's a useful asymmetry we can exploit: finding weights that perform well is computationally intensive and takes time, but scoring a set of weights is fast and easy. A number cruncher could spend 2 weeks training a model, and then when they submit the results it takes me 10 seconds to score the model - to verify the quality of the results, and calculate the performance-based payout. In the #1 or #3 scenario where they didn't do or didn't complete…

Paper and discussion history. A mention is not an endorsement.

Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network · HackerPapers discussions

Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network — mentioned by mitchellpkt