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

D2M: Dynamic Defense and Modeling of Adversarial Movement in Networks

Scott Freitas, Andrew Wicker, Duen Horng (Polo) Chau, Joshua Neil

2020 SIAM International Conference on Data Mining | December 2020

Microsoft Research Blog

Research at Microsoft 2020: Addressing the present while looking to the future

December 17, 2020 | Eyal Ofek, Jenn Wortman Vaughan, Hanna Wallach, Ed Cutrell, Josh Benaloh, Craig Costello, Christian Paquin, Akshay Krishnamurthy, Devon Hjelm, Sam Devlin, Katja Hofmann

Microsoft researchers pursue the big questions about what the world will be like in the future and the role technology will play. Not only do they take on the responsibility of exploring the long-term vision…

Video

Investigating Secure Development In Practice A Human-Centered Perspective

December 16, 2020 | Michelle Mazurek

Secure development is not just a technical problem: it’s a human and organizational problem as well. To understand the causes of insecurity, and find effective solutions, we must understand how and why security problems happen,…

the video title slide for Michelle Mazurek's session during the Developing Secure Systems Summit

01:37:15

Event

Developing Secure Systems Summit – Online Seminar Series: Fall 2020

December 16, 2020 | Virtual/Online

The Developing Secure Systems Summit (DS3) is meant to be an inclusive event, building on several existing communities to forge its identity. On the one hand, we aim to reach out to the security research…

illustration lines at different angles with intersection points representing connected network systems

Publication

An Attack on Some Signature Schemes Constructed from Five-Pass Identification Schemes

Daniel Kales, Greg Zaverucha

CANS 2020, Conference on Cryptology and Network Security | December 2020

Best paper award

Project Project

Publication

Identification of Significant Permissions for Efficient Android Malware Detection

Hemant Rathore, Sanjay K. Sahay, Ritvik Rajvanshi, Mohit Sewak

2020 Broadband Communications, Networks and Systems | December 2020

Publication

Cryptanalysis of LowMC instances using single plaintext/ciphertext pair

Betül Durak, Subhadeep Banik, Khashayar Barooti, Serge Vaudenay

FAST | December 2020

Best Paper Award

Publication

Detection of Malicious Android Applications: Classical Machine Learning vs. Deep Neural Network Integrated with Clustering

Hemant Rathore, Sanjay K. Sahay, Shivin Thukral, Mohit Sewak

2020 Broadband Communications, Networks and Systems | December 2020

Video

Trustworthy Machine Learning: Past, Present, and Future

December 9, 2020 | Somesh Jha

For the fourth session of the Developing Secure Systems Summit Online Seminar Series, Somesh Jha talked about Trustworthy Machine Learning: Past, Present and Future.

01:41:13

Publication

UnMask: Adversarial Detection and Defense Through Robust Feature Alignment

Scott Freitas, Shang-Tse Chen, Zijie J. Wang, Duen Horng (Polo) Chau

2020 International Conference on Big Data | December 2020

Security, privacy, and cryptography

Highlights