Welcome! In DSPLab, our research focus is on trustworthy machine learning, cybercrime analysis, and cyber threat intelligence. Find us on GitHub for tools/datasets and on Twitter for latest news.

People

Faculty

Avatar

Birhanu Eshete

Principal Investigator

Graduate Students

Avatar

Abderrahmen Amich

Ph.D. Candidate

Avatar

Christine Carlton

M.Sc. Student

Avatar

Elie Rizk

M.Sc. Student

Alumni

Avatar

Ata Kaboudi

M.Sc. Student

Avatar

Abdullah Ali

M.Sc. Student

Avatar

Chevy Pawlik

Undergraduate Student

Avatar

Hassaan Ali

M.Sc. Student

Avatar

Hassan Ali

M.Sc. Student

Avatar

Ismat Jarin

Ph.D. Candidate

Avatar

Jon-Nicklaus Jackson

M.Sc. Student

Avatar

Majed Chamseddine

M.Sc. Student

Avatar

Olajide David

M.Sc. Student

Avatar

Zeineb Moalla

Undergraduate Student

Research Areas

*

Trustworthy Machine Learning

We study robustness (to training data poisoning, model evasion, model stealing), privacy (against training example membership inference), and the interaction among robustness, privacy, transparency, and fairness properties in machine learning.

Cyber Threat Intelligence

Our focus is on systematic curation, characterization, measurement, and forensics of cyber threat intelligence (e.g., malware samples, infection traces, natural language threat descriptions).

Cybercrime Analysis

We focus on analysis, reconstruction, measurement, and defense of cybercrime with focus on cybercrime activities (e.g., phishing, malware) cybercrimen toolkits (e.g., exploit kits, ransomware, and APTs).

Recent Publications

(2023). Designing Secure Performance Metrics for Last-Level Cache. Proceedings of the 28th International Workshop on High-Level Parallel Programming Models and Supportive Environments (HIPS 2023).

(2022). Adversarial Detection of Censorship Measurements. Proceedings of the 21st ACM Workshop on Privacy in the Electronic Society (WPES’22), co-located with the 29th ACM Conference on Computer and Communications Security (CCS), 2022.

Project

(2022). DP-UTIL: Comprehensive Utility Analysis of Differential Privacy in Machine Learning. Proceedings of the 12th ACM Conference on Data and Application Security and Privacy (ACM CODASPY).

PDF Code Project Video

Contact