Esfandiar Mohammadi
Scholar

Esfandiar Mohammadi

Google Scholar ID: O9Z2mN8AAAAJ
Universität zu Lübeck
Differential PrivacyPrivacy-Preserving Machine LearningAnonymous Communication
Citations & Impact
All-time
Citations
563
 
H-index
12
 
i10-index
12
 
Publications
20
 
Co-authors
39
list available
Resume (English only)
Academic Achievements
  • - IEEE S&P 2025 paper: 'Mixnets on a tightrope: Quantifying the leakage of mix networks using a provably optimal heuristic adversary'
  • - ICPM 2024 paper: 'Differentially Private Inductive Miner'
  • - CCS 2024 paper: 'S-BDT: Frugal Differentially Private Gradient Boosting Decision Trees'
  • - CCS 2024 paper: 'DPM: Clustering Sensitive Data through Separation'
  • - CSF 2024 paper: 'Divide and Funnel: a Scaling Technique for Mix-Networks'
  • - VeDS project, funded by the state of Schleswig-Holstein, working on a trustworthy electricity marketplace and privacy-preserving distributed energy consumption prediction
Research Experience
  • - Tenured W2 (associate) professor at University of Lübeck since 2019
  • - Worked as a postdoctoral ZISC fellow at ETH Zürich from 2016 to 2019
  • - Head of the Privacy & Security (PrivSec) group at the Institute for IT-Security, University of Lübeck
  • - Director of the AnoMed competence cluster
Education
  • - Ph.D., Saarland University, Supervisor: Michael Backes, 2015
  • - Postdoctoral ZISC fellow, ETH Zürich, Host: David Basin, 2016-2019
Background
  • - Privacy & security in machine learning
  • - Differential privacy
  • - Anonymous communication
  • - Formal verification methods and their computational soundness
Miscellany
  • - Delighted to work with a group of talented people
  • - Scientific service: Program committee member for multiple conferences including ACM Conference on Computer and Communications Security (CCS), IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), USENIX Security Symposium, and more