Building Safe AI: A Tutorial on Homomorphically Encrypted Deep Learning

TLDR: In this blogpost, we’re going to train a neural network that is fully encrypted during training (trained on unencrypted data). The result will be a neural network with two beneficial properties. First, the neural network’s intelligence is protected … Read more


Risks of AI

tl;dr: Artificial intelligence is likely to become more powerful than humans some day. Most superintelligent systems will by default develop instrumental subgoals that conflict with human interests. This could have catastrophic consequences. If we don't a... (more…)

Read more »