Piotr (Peter) Mardziel

CMU Silicon Valley
Office: B23 114

Piotr (Peter) Mardziel

About me

I'm a systems scientist at CMU where I work on transparency and accountability in machine learning with applications to privacy and fairness.

Previously I was a PhD student and post-doc in the Programming Languages at University of Maryland (PLUM) group where I worked on probabilistic programming with applications for privacy and quantitative information flow. My interests include:

S&P Topics:
  • Anonymity
  • Language-based security
  • Machine learning and AI security
  • Privacy technologies and mechanisms
  • Secure information flow
CSF Topics:
  • accountability
  • anonymity and privacy
  • formal methods and verification
  • information flow control
  • language-based security
  • machine learning
  • software security
CMU Keywords:
  • Computer Systems: Security and Privacy:
    Foundations and Formal Methods, Analytics and Machine Learning
  • Signal Processing, Communications and Controls: Theoretical Foundations:
    Information Theory
  • Computer Systems: Application Domains:
    Machine learning
  • Signal Processing, Communications and Controls: Data Science:
    Machine Learning, Deep Learning


Current Students

MS/UG/HS Projects

  • Linear Diagnostics for Causal Learning
    Students: (MS) Joseph Konan
  • Explanations for Machine Vision
    Students: (MS) Ruili Zhu (MS) Siddharth Mehta (HS) Sahil Jain
    Former students: (MS) Bonan Jin (MS) Yucai Fan (MS) Dharini Krishna
  • Gender Bias in Natural Language Processing
    Students: (MS) Wan Wei (MS) Gaurav Shegokar
    Former students: (UG) Aashai Avadhani
  • Explanations for Spatio-Temporal Deep Learning
    Former students: (MS) Yi-Ping Hsu (MS) Zilu Zhang
  • Explanations for Deep Reinforcement Learning
    Former students: (MS) Jakob Cassiman
  • Deep Malware Classification
    Former students: (MS) Raj Gupta


Other service


Tech-reports / Pre-prints