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

当前选择

排序方式: 最新

清除选择

在这些结果中搜索

内容类型

发布日期

论文与出版物

BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI

Chengquan Guo, Yuzhou Nie, Chulin Xie, Zinan Lin, Wenbo Guo, Bo Li

ICML 2026 | October 2026

论文与出版物

Principled Design of Indexing Functions for Memory Coloring

Stephan Dübler, Jana Hofmann, Boris Köpf, Stavros Volos

35th USENIX Security Symposium | August 2026

项目

论文与出版物

What humanity needs to flourish in the next decade

E. Glen Weyl, James Evans, Chris White

Noema | July 2026

微软研究院博客

Verifying Rust cryptography in SymCrypt, from standards to code

2026年7月13日 | Son Ho, Cédric Fournet, Antoine Delignat-Lavaud, Samuel Lee, Jason Fisher, Jessica Krynitsky

Cryptographic code supports vital protections in modern computing systems. Learn how a new method helps verify code as developers write it while preserving speed and adaptability as it gets implemented and evolves.

Diagram showing the process of verifying cryptographic code. An algorithm from a standard is converted into a formal specification, while Rust code is converted into a code model. The specification and code model are then compared through proof and verification steps.

论文与出版物

HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment

Shei Pern Chua, Hao Wu, Qianli Ma, Fangzhao Wu

July 2026

arXiv | July 2026

论文与出版物

Differentially Private Synthetic Data via APIs 4: Tabular Data

Toan Tran, Arturs Backurs, Zinan Lin, Victor Reis, Li Xiong, Sergey Yekhanin

ICML 2026 | July 2026

项目

岗位

Applied Sciences Intern

Posted: 2026年6月30日

地点: Bangalore, Karnataka, India; Gurgaon, Haryana, India; Hyderabad, Telangana, India; India; Mumbai, Maharashtra, India; New Delhi, India; Noida, Uttar Pradesh, India; Pune, Maharashtra, India

研究领域: Artificial intelligence, Data platforms and analytics, Security, privacy, and cryptography

As an Applied Science Intern at Microsoft, you will be at the forefront of technological innovation, working collaboratively to bring research to life in our products and services. You’ll gain expertise in cutting-edge research areas,…

论文与出版物