illustration of lock, four asterisks and a shield with a fingerprint on it on a green gradient background

Security, privacy, and cryptography

Leveraging Large Language Models for Automated Proof Synthesis in Rust

photos of PhD students Anunay Kulshrestha and Karan Newatia with a photo of Senior Cryptographer Josh Benaloh in the middle with a microphone icon on a blue and purple gradient background

Intern Insights: Dr. Josh Benaloh with Anunay Kulshrestha and Karan Newatia

Bayes Security (β*, higher better) of DP-SGD against membership and attribute inference on the Adult and Purchase datasets as a function of the number of training steps. The green dashed line shows the corresponding DP budget (ε). Membership and attribute inference curves decrease monotonically as the model is trained for longer and the accuracy and DP budget grow.

Closed-Form Bounds for DP-SGD against Record-level Inference

ProvCam: A Camera Module with Self-Contained TCB for Producing Verifiable Videos

Current selections

Sort by: Most recent

Clear selections

Search within these results

Content Types

Published Date

Publication

A Verified, Efficient Embedding of a Verifiable Assembly Language

Aymeric Fromherz, Nick Giannarakis, Chris Hawblitzel, Bryan Parno, Aseem Rastogi, Nikhil Swamy

Principles of Programming Languages (POPL 2019) | January 2019

Project

Microsoft Research Blog

Microsoft Research 2018: 10 memorable blogs topping a year of open source and innovation

December 27, 2018

The year’s end is an opportunity to reflect on what was achieved and to resolve to aspire to even greater heights in the one that’s about to begin. Looking back on what was accomplished at…

Publication

Imperfect forward secrecy: how Diffie-Hellman fails in practice

David Adrian, Karthik Bhargavan, Zakir Durumeric, Pierrick Gaudry, Matthew Green, J. Alex Halderman, Nadia Heninger, Drew Springall, Emmanuel Thomé, Luke Valenta, Benjamin VanderSloot, Eric Wustrow, Santiago Zanella-Béguelin, Paul Zimmermann

Communications of The ACM | December 2018, Vol 62(1): pp. 106-114

Tool

Simple Encrypted Arithmetic Library (SEAL)

Microsoft Simple Encrypted Arithmetic Library (Microsoft SEAL) is an easy-to-use homomorphic encryption library developed by researchers in the Cryptography Research group at Microsoft Research. SEAL is written in modern standard C++ and has no external…

GitHub

Microsoft Research Blog

The Microsoft Simple Encrypted Arithmetic Library goes open source

December 3, 2018 | Kristin Lauter, Kim Laine, Sreekanth Kannepalli

Today we are extremely excited to announce that our Microsoft Simple Encrypted Arithmetic Library (Microsoft SEAL), an easy-to-use homomorphic encryption library developed by researchers in the Cryptography Research group at Microsoft, is open source on…

The Microsoft Simple Encrypted Arithmetic Library goes open source

Publication

State Separation for Code-Based Game-Playing Proofs

Chris Brzuska, Antoine Delignat-Lavaud, Cédric Fournet, Konrad Kohbrok, Markulf Kohlweiss

Asiacrypt | December 2018

Publication

Contamination Attacks and Mitigation in Multi-Party Machine Learning

Jamie Hayes, Olya Ohrimenko

Neural Information Processing Systems (NeurIPS) | December 2018

Project

Video

Tomas Palmer and Tolga Acar – Crypto in Windows Vista

November 29, 2018 | Tolga Acar, Tomas Palmer

Back in the day when I was a Program Manager in Windows overseeing Windows Crypto, and shipping CNG for the first time.

Publication

Secure Computation using Leaky Correlations (Asymptotically Optimal Constructions)

Alexander R. Block, Divya Gupta, Hemanta Maji, Hai H. Nguyen

TCC | November 2018

Tool

miTLS

miTLS is a verified reference implementation of the TLS protocol. Our code fully supports its wire formats, ciphersuites, sessions and connections, re-handshakes and resumptions, alerts and errors, and data fragmentation, as prescribed in the RFCs;…

GitHub

Security, privacy, and cryptography

Highlights