Security, privacy, and cryptography
Video
Generalization Error Bounds for Extreme Multi-class Classification
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels. Many applications have been found in diverse areas ranging from language modeling to document…
Video
A Parallel Primal-Dual Sparse Method for Extreme Classification
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels. Many applications have been found in diverse areas ranging from language modeling to document…
Video
Tight Learning Bounds for Multi-Class Classification
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels. Many applications have been found in diverse areas ranging from language modeling to document…
Podcast
New Microsoft Research Podcast invites you to log on, tune in and geek out
Microsoft Research Podcast Subscribe and listen on iTunes, android or email I’ve spent the better part of the last decade investigating the impact of digital media and technology on culture from an academic perspective. I…
Publication
Collecting Telemetry Data Privately
Video
Fiat Cryptography: Automatic Correct-by-Construction Generation of Low-Level Cryptographic Code
Some of the most widely used cryptographic protocols, including TLS, depend on fast execution of modular big-number arithmetic. Cryptographic primitives are coded by an elite set of implementation experts, and most programmers are shocked to…
Microsoft Research Blog
Neural fuzzing: applying DNN to software security testing
Microsoft researchers have developed a new method for discovering software security vulnerabilities that uses machine learning and deep neural networks to help the system root out bugs better by learning from past experience. This new…
Publication
ShrinkWrap: VTable Protection Without Loose Ends
Project
Microsoft SEAL
Microsoft SEAL—powered by open-source homomorphic encryption technology—provides a set of encryption libraries that allow computations to be performed directly on encrypted data.