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

Security, privacy, and cryptography

lock icon on green background

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

MSR Systems Networking Graphic

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

Current selections

Sort by: Most recent

Clear selections

Publication

BeeGees: Stayin’ Alive in Chained BFT

Neil Giridharan, Florian Suri-Payer, Matthew Ding, Heidi Howard, Ittai Abraham, Natacha Crooks

Symposium on Principles of Distributed Computing (PODC) | June 2023

Publication

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li

NeurIPS 2023 | June 2023

Outstanding Paper Award

Dataset Source Code

Analyzing PII Leakage

This repository contains the official code for our IEEE S&P 2023 paper using GPT-2 language models and Flair Named Entity Recognition (NER) models. It allows fine-tuning (i) undefended, (ii) differentially-private and (iii) scrubbed language models…

Podcast

Collaborators: Gov4git with Petar Maymounkov and Kasia Sitkiewicz

May 3, 2023

Collaboration is key to bringing ideas from lab to life. In the first episode of the #MSRPodcast series “Collaborators,” learn how GitHub’s Kasia Sitkiewicz and Protocol Labs’ Petar Maymounkov are teaming up to make open-source…

GitHub Product Manager Kasia Sitkiewicz and Protocol Labs Research Scientist Petar Maymounkov discuss their collaboration on Gov4git on the Microsoft Research Podcast

Publication

Analyzing Leakage of Personally Identifiable Information in Language Models

Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin

2023 IEEE Symposium on Security and Privacy | May 2023

Publication

SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

Ahmed Salem, Giovanni Cherubin, David Evans, Boris Köpf, Andrew Paverd, Anshuman Suri, Shruti Tople, Santiago Zanella-Béguelin

2023 IEEE Symposium on Security and Privacy | May 2023

Publication

How effective is multifactor authentication at deterring cyberattacks?

Lucas A. Meyer, Sergio Romero, Gabriele Bertoli, Tom Burt, Alex Weinert, Juan M. Lavista Ferres

May 2023

Publication

Hide and Seek with Spectres: Efficient discovery of speculative information leaks with random testing

Oleksii Oleksenko, Marco Guarnieri, Boris Köpf, Mark Silberstein

IEEE Symposium on Security and Privacy (S&P) | May 2023

Project Project

Publication

Denoising Masked Auto-encoders Helps Robust Classification

QuanLin Wu, Hang Ye, Yuntian Gu, Huishuai Zhang, Liwei Wang, Di He

International Conference on Learning Representations (ICLR) 2023 | May 2023

Publication

Memory Protection Keys: Facts, Key Extension Perspectives, and Discussions

Soyeon Park, Sangho Lee, Taesoo Kim

IEEE Security & Privacy | May 2023, Vol 21(3)