FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning

1 code implementation • 5 Apr 2020 • Sameer Wagh, Shruti Tople, Fabrice Benhamouda, Eyal Kushilevitz, Prateek Mittal, Tal Rabin

For private training, we are about 6x faster than SecureNN, 4. 4x faster than ABY3 and about 2-60x more communication efficient.

PAC learning with nasty noise

no code implementations • Theoretical Computer Science 2002 • Nader H Bshouty, Nadav Eiron, Eyal Kushilevitz

We introduce a new model for learning in the presence of noise, which we call the Nasty Noise model.

PAC learning