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

Agatha: Smart Contract for DNN Computation

Zihan Zheng, Peichen Xie, Xian Zhang, Shuo Chen, Yang Chen, Xiaobing Guo, Guangzhong Sun, Guangyu Sun, Lidong Zhou

May 2021

Microsoft Research Blog

EverParse: Hardening critical attack surfaces with formally proven message parsers

May 3, 2021 | Tahina Ramananandro, Aseem Rastogi, Nikhil Swamy

EverParse (opens in new tab) is a framework for generating provably secure parsers and formatters used to improve the security of critical code bases at Microsoft. EverParse is developed as part of Project Everest (opens…

Video

Practical Secure Inference | Asia Innovation Summit

May 3, 2021 | Divya Gupta

Fueled by massive data and the availability of extensive compute, sophisticated machine learning models have found diverse applications across verticals such as healthcare and finance. This has made the problem of privacy-preserving machine learning increasingly…

31:42

Publication

Privacy-preserving decentralized aggregation for federated learning

Beomyeol Jeon, SM Ferdous, Muntasir Raihan Rahman, Anwar Walid

IEEE INFOCOM 2021 – IEEE Conference on Computer Communications Workshops (INFOCOM WORKSHOPS) | May 2021

Publication

Hardware-Software Contracts for Secure Speculation

Marco Guarnieri, Boris Köpf, Jan Reineke, Pepe Vila

IEEE Symposium on Security and Privacy | May 2021

Best Paper Award

Project Project

Publication

A Security Model and Fully Verified Implementation for the IETF QUIC Record Layer

Antoine Delignat-Lavaud, Cédric Fournet, Bryan Parno, Jonathan Protzenko, Tahina Ramananandro, Jay Bosamiya, Joseph Lallemand, Itsaka Rakotonirina, Yi Zhou

IEEE Symposium on Security and Privacy | May 2021

Project

Publication

Anomalicious: Automated Detection of Anomalous and Potentially Malicious Commits on GitHub

Danielle Gonzalez, Thomas Zimmermann, Patrice Godefroid, Max Schaefer

International Conference on Software Engineering (ICSE), Software Engineering in Practice (SEIP) track | May 2021

Project Project

Publication

Characterizing Ethereum’s Mining Power Decentralization at a Deeper Level

Liyi Zeng, Yang Chen, Shuo Chen, Xian Zhang, Zhongxin Guo, Wei Xu, Thomas Moscibroda

IEEE Conference on Computer Communications (INFOCOM) | May 2021

Event

Race and Technology: A Research Lecture Series

May 1, 2021 – June 30, 2022 | Virtual

You’re invited to join us as we bring together leading voices at the intersection of race and technology for discussions around data, the internet, justice, genomics and more. In this virtual speaker series, connect with the distinguished academics and domain experts who are driving this…

Race & Technology, A Research Lecture Series

Publication

Beyond Security and Efficiency: On-Demand Ratcheting with Security Awareness

Betül Durak, Andrea Caforio, Serge Vaudenay

PKC | May 2021

Security, privacy, and cryptography

Highlights