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

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

Yuxin (Myles) Liu, Zhihao Yao, Mingyi Chen, Ardalan Amiri Sani, Sharad Agarwal, Gene Tsudik

MobiCom | November 2024

Tool

Crescent

Crescent adds privacy to existing credentials with zero-knowledge. Crescent is a library to generate proofs of possession of JSON Web Tokens (JWT) and mobile Driver’s Licenses (mDL) credentials. By creating a proof for a JWT…

GitHub

Publication

Exploring Continual Fine-Tuning for Enhancing Language Ability in Large Language Model

Divyanshu Aggarwal, Sankarshan Damle, Navin Goyal, Satya Lokam, Sunayana Sitaram

NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability | October 2024, Vol abs/2410.16006

Microsoft Research Blog

Research Focus: Week of October 7, 2024

October 9, 2024

Simplifying secure decision tree training; Improving accuracy of audio content detection; A novel neurosymbolic system for converting text to tables; New video series: AI for Business Transformation; TEE security protections for container workloads.

Publication

Confidential Container Groups: Implementing Confidential Computing on Azure Container Instances

Matthew Johnson, Stavros Volos, Ken Gordon, Sean T. Allen, Sylvan Clebsch, Christoph M. Wintersteiger, John Starks, Manuel Costa

Communications of the ACM | October 2024, Vol 67(10): pp. 40-49

Project

Publication

Secure Sorting and Selection via Function Secret Sharing

Amit Agarwal, Elette Boyle, Nishanth Chandran, Niv Gilboa, Divya Gupta, Yuval Ishai, Mahimna Kelkar, Yiping Ma

31st Annual Conference on Computer and Communications Security (ACM CCS 2024) | October 2024

Project

Publication

Principled Microarchitectural Isolation on Cloud CPUs

Stavros Volos, Cédric Fournet, Jana Hofmann, Boris Köpf, Oleksii Oleksenko

ACM Conference on Computer and Communications Security (CCS) | October 2024

CCS Distinguished Paper Award

Project

Publication

Gaussian Elimination of Side-channels: Linear Algebra for Memory Coloring

Jana Hofmann, Cédric Fournet, Boris Köpf, Stavros Volos

ACM Conference on Computer and Communications Security (CCS) | October 2024

Project

Publication

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

Chengquan Guo, Xun Liu, Chulin Xie, Andy Zhou, Yi Zeng, Zinan Lin, Dawn Song, Bo Li

NeurIPS 2024 | October 2024

Microsoft Research Blog

Research Focus: Week of September 9, 2024

September 12, 2024 | Sara Abdali, Sefik Emre Eskimez, Xiaofei Wang, Manthan Thakker, Jinyu Li, Sheng Zhao, Naoyuki Kanda, Carmen Badea, Christian Bird, Tom Zimmermann, Rob DeLine, Nicole Forsgren, Denae Ford Robinson, Xenofon Foukas

Investigating vulnerabilities in LLMs; A novel total-duration-aware (TDA) duration model for text-to-speech (TTS); Generative expert metric system through iterative prompt priming; Integrity protection in 5G fronthaul networks:

Security, privacy, and cryptography

Highlights