Security Research Projects

Analytical Framework to Quantify Information Leakage and Memorization in Machine Learning

Reza SHOKRI

Machine learning models can "memorize" specific data points from their training data, impacting their predictions and potentially leaking sensitive information. This project aims to understand how this memorization affects models and develop methods to mitigate it.

Fuzz Testing

Abhik ROYCHOUDHURY

• 
• TRL 4
• Software Security & Analysis

BCube and Flint: Overcoming the 50% Barrier in Blockchains

YU Haifeng

Computational Hardness Assumptions and the Foundations of Cryptography

Prashant Nalini VASUDEVAN

This program seeks to broaden and diversify the foundations of cryptography by identifying new plausible computational hardness assumptions that can be used to construct cryptosystems. Our current approach is to study and construct "fine-grained" cryptographic primitives based on the conjectured hardness of various well-studied algorithmic problems.

• 
• Cryptography

SQLancer: Automatic Testing of Database Management Systems

Manuel RIGGER

SQLancer automatically finds logic bugs in Database Management Systems (DBMSs). We have used SQLancer to find and report over 500 unique, previously unknown bugs in widely-used DBMSs. In addition, SQLancer has been widely adopted in the industry.

• 
• TRL 9
• Software Testing

From iteration on multiple collections in synchrony to fast general interval joins

WONG Lim Soon

Synchrony iterator captures a programming pattern for synchronized iterations. It is a conservative extension that enhances the repertoire of algorithms expressible in comprehension syntax. In particular, efficient general synchronized iterations, e.g. linear-time algorithms for low-selectivity database non-equijoins, become expressible naturally in comprehensinon syntax.

• 
• TRL 4

National Cybersecurity R&D Laboratory

CHANG Ee Chien

• 
• Infrastructure Security & Experimentation

Automated Program Repair

Abhik ROYCHOUDHURY

• 
• 
• 
• TRL 4
• Software Security & Analysis

Active Defense Mechanism against Adversarial Attacks

CHANG Ee Chien

• Machine Learning & AI Security

Intelligent Modelling for Decision-Making in Critical Urban Systems - DesCartes

Abhik ROYCHOUDHURY

Trustworthy de-centralized (federated) learning

Reza SHOKRI

Robustness and security in machine learning

Reza SHOKRI

Auditing data privacy (in machine learning)

Reza SHOKRI