Security, privacy, & cryptography
Developing technologies that protect data, preserve privacy, and build trustworthy computing systems.
Video
Protecting People from Algorithms (and Vice Versa)
Computing technologies today have made it much easier to gather personal data. Algorithms are constantly analyzing such personal information and making consequential decisions on people. The extensive use of algorithms imposes the risks of algorithms…
Microsoft Research Blog
Microsoft Research PhD fellowships provide financial support to promising researchers
By Jim Pinkelman, Senior Director, Microsoft Research Since 2008, Microsoft Research has been awarding two-year PhD fellowships to computer science and related researchers at leading universities in the United States and Canada. These awards are…
Video
Towards Practical Machine Learning with Differential Privacy and Beyond
Machine learning (ML) has become one of the most powerful classes of tools for artificial intelligence, personalized web services and data science problems across fields. However, the use of ML on sensitive data sets involving…
Publication
Learn&Fuzz: Machine Learning for Input Fuzzing
Video
Quantum Algorithms for Number Theory and their Relevance to Cryptography
I will report on recent results about quantum algorithms for solving computational problems in number theory. I will show how they impact the security of certain post-quantum cryptosystems. Shor’s quantum algorithm for factoring large integers…
Video
Leveraging Privacy in Data Analysis
My research focuses on applying differential privacy to problems in economics, statistical hypothesis testing, and adaptive data analysis in machine learning. At a high level, a differential private algorithm limits the sensitivity of the outcome…
Video
Towards Practical Machine Learning with Differential Privacy and Variants
Machine learning (ML) has become one of the most powerful classes of tools for artificial intelligence, personalized web services and data science problems across fields. However, the use of ML on sensitive data sets involving…
Publication
Hierarchical Functional Encryption
Project
Microsoft Security Risk Detection
The Microsoft Security Risk Detection Service (MSRD) was discontinued effective June 25, 2020. This service from Microsoft Research provided users with a premium software testing experience, searching for vulnerabilities in native code with the power…