dp-transformers
Training transformer models with differential privacy Transformer models have recently taken the field of Natural Language Processing (NLP) by storm as large language models based on the transformer architecture have shown impressive performance across a…
Accelerating the Delfs-Galbraith algorithm with fast subfield root detection
In this talk, we discuss the general supersingular isogeny problem, the foundational hardness assumption underpinning isogeny-based cryptography. We implement and optimize the best attack against this problem – the Delfs-Galbraith algorithm – to explicitly determine…
Confidential Containers: Verifiably secure computation in the cloud
For many organizations, trusting their data to the cloud requires having a complete understanding of and control over the environment in which that data resides and how it’s being processed. Microsoft understands this, and we…