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

Pointer Tagging for Memory Safety

Tony Chen, David Chisnall

MSR-TR-2019-17 | July 2019

Published by Microsoft

Project

Publication

Decentralized & Collaborative AI on Blockchain

Justin D. Harris, Bo Waggoner

2019 IEEE International Conference on Blockchain (Blockchain) | July 2019

Github Project

Publication

libmpk: Software Abstraction for Intel Memory Protection Keys (Intel MPK)

Soyeon Park, Sangho Lee, Wen Xu, Hyungon Moon, Taesoo Kim

2019 USENIX Annual Technical Conference (ATC 2019) | July 2019

Video

How To: Integrate MSRD with Azure DevOps

June 28, 2019 | David Molnar

Microsoft Security Risk Detection: How to integrate MSRD with Azure DevOps

0:07:49

Video

How To: Microsoft Security Risk Detection (Web Vulnerability Scanning)

June 28, 2019 | Ram Nagaraja

Microsoft Security Risk Detection – How to use MSRD to perform Web App Scanning

0:08:51

Video

How to: Microsoft Security Risk Detection (Fuzzing)

June 28, 2019 | Ram Nagaraja

Microsoft Security Risk Detection (MSRD): How to fuzz

Video: Microsoft Security Risk Detection

0:27:38

Tool

Vale

Vale (Verified Assembly Language for Everest) is a tool for constructing formally verified high-performance assembly language code, with an emphasis on cryptographic code. It uses existing verification frameworks, such as Dafny and F*, for formal…

GitHub Publication Publication Publication

Tool

EverCrypt

EverCrypt (opens in new tab) is a high-performance, cross-platform, formally verified modern cryptographic provider distributed as a combined C/ASM library. EverCrypt packages cryptographic implementations from the HACL* and ValeCrypt projects, and automatically picks the fastest…

GitHub Publication Publication Publication Publication Publication

Tool

FStar

F*: Verification system for effectful programs

GitHub Publication

Video

PASTA: PASsword-based Threshold Authentication

June 24, 2019 | Peihan Miao

We introduce and formalize a new notion of password-based threshold token authentication, which protects password-based authentication against single point of failures. Specifically, we distribute the role of a single server among n servers and allow…

Peihan Miao giving a talk at Microsoft Research

0:45:41

Security, privacy, and cryptography

Highlights