Hi, I'm Matteo Boglioni
Research Intern at Mila, previously MSc at ETH Zürich. I focus on red-teaming and model auditing to uncover AI vulnerabilities and improve robustness, security, and responsible deployment.
About Me
I'm particularly interested in red-teaming and model auditing as proactive techniques to uncover existing models' vulnerabilities. I aim to assess and expose flaws and inconsistencies, both in performance and security, to increase robustness and reliability towards distribution shifts, adversarial inputs, and unintended behaviors.
I believe this step is crucial for a responsible and ethical deployment of AI.
When I'm not doing research
Latest Posts
Experience
Education and professional experience.
Research Intern
Research on local precision auditing of machine unlearning methods.
MSc Computer Science — Machine Intelligence
Focus on machine learning, AI safety, and robustness. Thesis on privacy auditing of DP-SGD.
Visiting Research Scholar
Research on Differential Privacy Auditing, under Prof. Zhiwei Steven Wu.
ECE Visiting Student
Exchange semester in Electrical and Computer Engineering.
BSc Engineering of Computing Systems
Undergraduate studies in computer engineering with focus on systems and software development.
Publications
Selected research publications.
Get In Touch
Feel free to reach out for collaborations or questions.