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

People

Published Date

Publication

Scalable Extraction of Training Data from (Production) Language Models

Milad Nasr, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A. F. Cooper, Daphne Ippolito, Christopher A. Choquette-Choo, Eric Wallace, Florian Tramèr, Katherine Lee, A. Feder Cooper

ICLR 2025 | November 2023

Publication

Hacksaw: Hardware-Centric Kernel Debloating via Device Inventory and Dependency Analysis

Zhenghao Hu, Sangho Lee, Marcus Peinado

30th ACM Conference on Computer and Communications Security (CCS 2023) | November 2023

Microsoft Research Blog

Research Focus: Week of November 22, 2023

November 22, 2023

A new deep-learning compiler for dynamic sparsity; Tongue Tap could make tongue gestures viable for VR/AR headsets; Ranking LLM-Generated Loop Invariants for Program Verification; Assessing the limits of zero-shot foundation models in single-cell biology.

Publication

Splice: Efficiently Removing a User’s Data from In-memory Application State

Xueyuan Han, James Mickens, Siddhartha Sen

2023 Computer and Communications Security | November 2023

Publication

Leveraging Large Language Models for Automated Proof Synthesis in Rust

Jianan Yao, Ziqiao Zhou, Weiteng Chen, Weidong Cui

arXiv:2311.03739 | November 2023

Publication

CHERIoT: Complete Memory Safety for Embedded Devices

Saar Amar, David Chisnall, Tony Chen, Nathaniel Filardo, Ben Laurie, Kunyan Liu, Robert Norton-Wright, Simon W. Moore, Yucong Tao, Robert N. M. Watson, Hongyan Xia

2023 56th IEEE/ACM International Symposium on Microarchitecture (MICRO) | October 2023, pp. 641-653

Project

Publication

Siloz: Leveraging DRAM Isolation Domains to Prevent Inter-VM Rowhammer

Kevin Loughlin, Jonah Rosenblum, Stefan Saroiu, Alec Wolman (alecw), Dimitrios Skarlatos, Baris Kasikci

SOSP 2023 | October 2023

Project

Publication

Dynamic Linkers Are the Narrow Waist of Operating Systems

Charly Castes, Adrien Ghosn

October 2023

Microsoft Research Blog

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

October 16, 2023 | Boxin Wang, Bo Li, Zinan Lin

This paper received the outstanding benchmarks track paper award during NeurIPS 2023 (opens in new tab). How trustworthy are generative pre-trained transformer (GPT) models? To answer this question, University of Illinois Urbana-Champaign, together with Stanford…

White line icons on a blue and green gradient background

Publication

Confidential Consortium Framework: Secure Multiparty Applications with Confidentiality, Integrity, and High Availability

Heidi Howard, Fritz Alder, Eddy Ashton, Amaury Chamayou, Sylvan Clebsch, Manuel Costa, Antoine Delignat-Lavaud, Cédric Fournet, Andrew Jeffery, Matthew Kerner, Fotios Kounelis, Markus Kuppe, Julien Maffre, Mark Russinovich, Christoph M. Wintersteiger

Proceedings of the VLDB Endowment | October 2023, Vol 17(2)

Nominee for Best Paper Award

Project

Security, privacy, and cryptography

Highlights