Giovanni Cherubin
Scholar

Giovanni Cherubin

Google Scholar ID: wM290P0AAAAJ
Microsoft
Machine LearningConformal PredictionPrivacyInformation Leakage
Citations & Impact
All-time
Citations
1,310
 
H-index
16
 
i10-index
21
 
Publications
20
 
Co-authors
8
list available
Resume (English only)
Academic Achievements
  • Involved in various research projects and published multiple papers, including but not limited to:
  • - Evaluating website fingerprinting in the real world
  • - Reconstruction attacks against ML models
  • - Deploying and evaluating website fingerprinting attacks on the Tor network
  • - Exact Optimization of Conformal Predictors via Incremental and Decremental Learning
  • Awarded the Internet Defense Award (2nd place) and Distinguished Paper Award (USENIX '22).
Research Experience
  • Joined Microsoft Research Cambridge and the Microsoft Security Response Centre (MSRC) in February 2022, working as a Senior Researcher on all things ML, privacy-preserving ML, and security.
Background
  • Senior Researcher in Machine Learning & Security at Microsoft (Cambridge). Research interests: Information leakage estimation for security&privacy, Theory, foundations, and privacy-security properties of Machine Learning, Methods for distribution-free confident prediction in supervised learning and anomaly detection (e.g., Conformal Predictors). Co-founder of the CTF team TU6PM. A user of OpenBSD and QubesOS.
Miscellany
  • Personal interests include using OpenBSD and QubesOS operating systems.