About me

I am Robin Staab, a PhD student at the Secure, Reliable, and Intelligent Systems Lab of ETH Zürich, advised by Prof. Martin Vechev, since July 2023.

Education

  • ETH Zurich, 2020 - 2023
  • M. Sc. Computer Science

  • ETH Zurich, 2016 - 2020
  • B. Sc. Computer Science

Work Experience

  • Snyk , Aug-Dec 2021
  • Machine Learning Engineering Intern, Zurich

Awards

2023 Willi Studer Prize for Best Master's Degree in Computer Science Awarded

Publications

2024

From Principle to Practice: Vertical Data Minimization for Machine Learning
Robin Staab, Nikola Jovanović, Mislav Balunović, Martin Vechev
IEEE S&P 2024
Beyond Memorization: Violating Privacy Via Inference with Large Language Models
Robin Staab, Mark Vero, Mislav Balunović, Martin Vechev
ICLR 2024 Spotlight, 2024 PPPM-Award
Watermark Stealing in Large Language Models
Nikola Jovanović, Robin Staab, Martin Vechev
Workshop on Reliable and Responsible Foundation Models (R2-FM) -- ICLR 2024 Oral
Exploiting LLM Quantization
Kazuki Egashira, Mark Vero, Robin Staab, Jingxuan He, Martin Vechev
arXiv 2024
Private Attribute Inference from Images with Vision-Language Models
Batuhan Tömekçe, Mark Vero, Robin Staab, Martin Vechev
arXiv 2024
Large Language Models are Advanced Anonymizers
Robin Staab, Mark Vero, Mislav Balunović, Martin Vechev
arXiv 2024

2023

Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks
Mark Niklas Müller, Marc Fischer, Robin Staab, Martin Vechev
PLDI 2023

2022

Bayesian Framework for Gradient Leakage
Mislav Balunović, Dimitar I. Dimitrov, Robin Staab, Martin Vechev
ICLR 2022