Mathias Lecuyer

Assistant Professor

Research Interests

Machine learning systems
Guarantees of robustness, privacy, and security

Relevant Thesis-Based Degree Programs

 
 

Graduate Student Supervision

Master's Student Supervision

Theses completed in 2010 or later are listed below. Please note that there is a 6-12 month delay to add the latest theses.

A differentially private network traffic shaping framework (2023)

Many Internet applications depend exclusively on end-to-end encryption of network traffic as the primary means to guarantee the users' privacy. However, encryption alone cannot prevent network side-channel attacks--leaks of sensitive information through the sizes and timing of network packets. We present NetShaper, a traffic shaping framework to mitigate network side-channel attacks. NetShaper’s traffic shaping provides differential privacy guarantees, allowing users to adjust the trade-off between privacy guarantees and bandwidth overhead according to their specific requirements. We design NetShaper as a modular tunnel endpoint that can be deployed anywhere along the path of traffic. We implement a simulator to assess the privacy and bandwidth trade-offs of our framework and demonstrate its applicability in a video streaming and a web service and its effectiveness in thwarting state-of-the-art network side-channel attacks.

View record

 
 

If this is your researcher profile you can log in to the Faculty & Staff portal to update your details and provide recruitment preferences.

 
 

Read tips on applying, reference letters, statement of interest, reaching out to prospective supervisors, interviews and more in our Application Guide!