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

Securing AI Agents with Information-Flow Control

Manuel Costa, Boris Köpf, Aashish Kolluri, Andrew Paverd, Mark Russinovich, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin

May 2025

Project Project

Microsoft Research Blog

FrodoKEM: A conservative quantum-safe cryptographic algorithm

May 27, 2025 | Patrick Longa

The recent advances in quantum computing offer many advantages—but also challenge current cryptographic strategies. Learn how FrodoKEM could help strengthen security, even in a future with powerful quantum computers.

The image features a gradient background transitioning from blue on the left to pink on the right. In the center, there are three white icons. On the left is a microchip icon that represents quantum computing, in the middle is a shield, and on the right is another microchip with a padlock symbol inside it.

Publication

Dynamic Risk Assessments for Offensive Cybersecurity Agents

Boyi Wei, Benedikt Stroebl, Jiacen Xu, Joie Zhang, Zhou Li, Peter Henderson

NeurIPS 2025 | May 2025

Publication

Identifying Incoherent Search Sessions: Search Click Fraud Remediation Under Real-World Constraints

Runze Zhang, Ranjita Pai Sridhar, Mingxuan Yao, Zheng Yang, David Oygenblik, Haichuan Xu, Vacha Dave, Cormac Herley, Paul England, Brendan Saltaformaggio

2025 IEEE Symposium on Security and Privacy (SP) | May 2025

Microsoft Research Blog

Research Focus: Week of May 7, 2025

May 7, 2025

In this issue: New research on compound AI systems and causal verification of the Confidential Consortium Framework; release of Phi-4-reasoning; enriching tabular data with semantic structure, and more.

Publication

MicroNova: Folding-based arguments with efficient (on-chain) verification

Jiaxing Zhao, Srinath Setty, Weidong Cui, Greg Zaverucha

Security and Privacy | May 2025

Publication

Rollbaccine : Herd Immunity against Storage Rollback Attacks in TEEs

David C. Y. Chu, Aditya Balasubramanian, Dee Bao, Natacha Crooks, Heidi Howard, Lucky E. Katahanas, Soujanya Ponnapalli

May 2025

Publication

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities

Chung-En Sun, Xiaodong Liu, Weiwei Yang, Tsui-Wei Weng, Hao Cheng, Aidan San, Michel Galley, Jianfeng Gao

NAACL 2025 | April 2025

Selected for oral presentation

Tool

Open-Source Consent Package

A collection of packages for building consent management systems with audit trails, granular permissions, and flexible storage backends. Designed for transparency, compliance with privacy regulations, and easy integration into existing applications.

GitHub

Microsoft Research Blog

Research Focus: Week of April 21, 2025

April 23, 2025 | Emre Kiciman, Robert Osazuwa Ness, Amit Sharma, Sean Rintel, Leon Reicherts, Lev Tankelevitch, Advait Sarkar, Pratik Ghosh, Richard Banks, Xiaodong Liu, Weiwei Yang, Hao Cheng, Michel Galley, Jianfeng Gao, Serina Chang, Jake Hofman, Hannes Gamper

In this issue: our CHI 2025 & ICLR 2025 contributions, plus research on causal reasoning & LLMs; countering LLM jailbreak attacks; and how people use AI vs. AI-alone. Also, SVP of Microsoft Health Jim Weinstein…

Security, privacy, and cryptography

Highlights