Scholar
Mark Vero
Google Scholar ID: vguDYtQAAAAJ
Google, ETH Zurich
Citations & Impact
Citations
508
H-index
9
i10-index
9
Publications
15
Co-authors
25
list available
Publications
Resume (English only)
Academic Achievements
- 2025 Publications:
- Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation
- Fewer Weights, More Problems: A Practical Attack on LLM Pruning
- BaxBench: Can LLMs Generate Secure and Correct Backends?
- Black-Box Adversarial Attacks on LLM-Based Code Completion
- Mind the Gap: A Practical Attack on GGUF Quantization
- Finetuning-Activated Backdoors in LLMs
- Large Language Models are Advanced Anonymizers
- 2024 Publications:
- A Synthetic Dataset for Personal Attribute Inference
- Private Attribute Inference from Images with Vision-Language Models
- Exploiting LLM Quantization
- COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
- CuTS: Customizable Tabular Synthetic Data Generation
- Instruction Tuning for Secure Code Generation
- Beyond Memorization: Violating Privacy Via Inference with Large Language Models
- Back to the Drawing Board for Fair Representation Learning
- 2023 Publications:
- TabLeak: Tabular Data Leakage in Federated Learning
Research Experience
- Teaching Experience:
- 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
Background
- PhD student at the Department of Computer Science, ETH Zürich. Part of the Secure, Reliable, and Intelligent Systems Lab, supervised by Martin Vechev since July 2023.
