Jonas Schneider

Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World

2017 · arXiv (Cornell University)

Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores domain randomization, a simple technique for training models on simulated images that …

Membership Privacy for Fully Dynamic Group Signatures

2019 · IACR Cryptology ePrint Archive

Group signatures present a compromise between the traditional goals of digital signatures and the need for signer privacy, allowing for the creation of unforgeable signatures in the name of a group which reveal nothing about …