TECHNICAL WORKSHOP SERIES - Privacy-Preserving Computing Using Intel SGX (2nd Offering) by: Ali Abbasi Tadi

Thursday, June 13, 2024 - 14:00

Technical Workshop Series

 Privacy-Preserving Computing Using Intel SGX (2nd Offering)


Presenter:  Ali Abbasi Tadi, Ph.D. Candidate

Date: Thursday, June 13th, 2024

Time:  2:00 PM

Location: 4th Floor (Lecture Space) at 300 Ouellette Avenue (School of Computer Science Advanced Computing Hub)


This is a hands-on workshop; it is recommended that you bring your laptop.



In today‚Äôs world, where artificial intelligence has revolutionized every industry, the concerns about using AI models have also increased. One of these concerns is privacy in machine learning as a service. There is a challenge to finding a way to do machine learning computations in a cloud environment in a secure way. Intel Software Guard Extension (SGX) is an ideal tool for doing secure programming for machine learning. SGX allows private programming so that only the trusted entities can access the code and data of the training model.  This talk explores how to design a trusted program using Linux SGX SDK. We investigate the concepts of Intel SGX data structure, sealing, and attestation in the SGX environment. Also, we provide examples of doing secure programming without any unauthorized access from OS or a third party to the data. In addition, we will explore various frameworks to facilitate Intel SGX usage, such as Occlum introduced by Antgroup.


Workshop Outline:

The main idea of Intel SGX

How Intel SGX works

What is sealing?

What is attestation?

How to design a simple, secure program using Intel SGX



Shell scripting, C/C++ programming



Ali is pursuing his Ph.D. in computer science at the University of Windsor. His main research interest is privacy-preserving machine learning. He has publications on private computing in top-tier conferences and peer-reviewed journals. He has received various scholarships from the University of Windsor and got 5th place in the iDash Security Competition 2022.  He has been awarded for the best paper in Canadian AI 2022. He is developing a secure transformer framework for private computation in the cloud environment.



MAC STUDENTS ONLY - Register here