Mark Vero

About me

I am Mark Vero, a PhD student at the Department of Computer Science, ETH Zürich. I am part of the Secure, Reliable, and Intelligent Systems Lab, supervised by Martin Vechev, since July 2023.

Education

ETH Zurich, since July 2023
PhD Candidate in Computer Science
ETH Zurich, 2020 - 2023
Masters in Electrical Engineering and Information Technology
ETH Zurich, 2017 - 2020
Bachelors in Electrical Engineering and Information Technology

Teaching

Analysis 1, Autumn 2019, Autumn 2022
Analysis 2, Spring 2020, Spring 2022
Analysis 3, Autumn 2020
Introduction to Electrical Engineering, Spring 2019
Engineering Mechanics, Autumn 2018

Publications

2024

A Synthetic Dataset for Personal Attribute Inference

Hanna Yukhymenko, Robin Staab, Mark Vero, Martin Vechev

NeurIPS Datasets and Benchmarks 2024

Paper

Code

Private Attribute Inference from Images with Vision-Language Models

Batuhan Tömekçe, Mark Vero, Robin Staab, Martin Vechev

NeurIPS 2024

Paper

Code

Exploiting LLM Quantization

Kazuki Egashira, Mark Vero, Robin Staab, Jingxuan He, Martin Vechev

NeurIPS 2024 CC BY 4.0 by @fontawesome - https://fontawesome.com

NextGenAISafety@ICML24 Oral

Website

Paper

Code

COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act

Philipp Guldimann, Alexander Spiridonov, Robin Staab, Nikola Jovanović, Mark Vero, Velko Vechev, Anna Gueorguieva, Mislav Balunović, Nikola Konstantinov, Pavol Bielik, Petar Tsankov, Martin Vechev

arXiv 2024

Website

Paper

Code

Practical Attacks against Black-box Code Completion Engines

Slobodan Jenko, Jingxuan He, Niels Mündler, Mark Vero, Martin Vechev

arXiv 2024

Paper

CuTS: Customizable Tabular Synthetic Data Generation

Mark Vero, Mislav Balunović, Martin Vechev

ICML 2024

Paper