Get started
Author

Mark Vero

Observed name: Vero, Mark
Observed institutions: Google (United States), ETH Zurich
OpenAlex ID: A5005972528
Large Language Models are Advanced Anonymizers
2024 · Staab, Robin, Vero, Mark, et al. · arXiv (Cornell University) · 45
PDF
COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
2024 · Guldimann, Philipp, Spiridonov, Alexander, et al. · arXiv (Cornell University) · 42
PDF
BaxBench: Can LLMs Generate Correct and Secure Backends?
2025 · Vero, Mark, Mündler, Niels, et al. · arXiv (Cornell University) · 38
PDF
Private Attribute Inference from Images with Vision-Language Models
2024 · Batuhan Tömekçe, Mark Vero, et al. · neural information processing systems · 33
PDF
A Synthetic Dataset for Personal Attribute Inference
2024 · Hanna Yukhymenko, Robin Staab, et al. · neural information processing systems · 19
PDF
Black-Box Adversarial Attacks on LLM-Based Code Completion
2024 · Jenko, Slobodan, Mündler, Niels, et al. · arXiv (Cornell University) · 13
PDF
Mind the Gap: A Practical Attack on GGUF Quantization
2025 · Egashira, Kazuki, Staab, Robin, et al. · arXiv (Cornell University) · 11
PDF
CuTS: Customizable Tabular Synthetic Data Generation
2023 · Vero, Mark, Balunović, Mislav, et al. · arXiv (Cornell University) · 11
PDF
Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
2025 · Gloaguen, Thibaud, Vero, Mark, et al. · arXiv (Cornell University) · 8
PDF
Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR
2026 · Egashira, Kazuki, Vero, Mark, et al. · arXiv (Cornell University) · 7
PDF
Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation
2025 · De Muri, Giovanni, Vero, Mark, et al. · arXiv (Cornell University) · 6
PDF
Fewer Weights, More Problems: A Practical Attack on LLM Pruning
2025 · Egashira, Kazuki, Staab, Robin, et al. · arXiv (Cornell University) · 4
PDF
Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
2026 · Vero, Mark, Kaczmarczyck, Fabian, et al. · arXiv (Cornell University) · 3
PDF
SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization
2026 · Wang, Hao, Mündler, Niels, et al. · arXiv (Cornell University) · 3
PDF
Reducing neural architecture search spaces with training-free statistics and computational graph clustering
2022 · Thorir Mar Ingolfsson, Mark Vero, et al. · ACM International Conference on Computing Frontiers (CF) · 3
PDF
Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
2026 · Gloaguen, Thibaud, Staab, Robin, et al. · arXiv (Cornell University) · 2
PDF
AutoBaxBuilder: Bootstrapping Code Security Benchmarking
2025 · von Arx, Tobias, Mündler, Niels, et al. · arXiv (Cornell University) · 1
PDF
All-in-One: A Composable Attack on LLM Transformations
2026 · Zhan, Xiaohua, Egashira, Kazuki, et al. · arXiv (Cornell University)
PDF
Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
2026 · Feng, Yu-Du, Mündler-Sasahara, Niels, et al. · arXiv (Cornell University)
PDF
Widening the Gap: Exploiting LLM Quantization via Outlier Injection
2026 · Zhan, Xiaohua, Egashira, Kazuki, et al. · arXiv (Cornell University)
PDF
AutoBaxBuilder: Bootstrapping Code Security Benchmarking
2025 · von Arx, Tobias, Mündler, Niels, et al. · Repository for Publications and Research Data (ETH Zurich)
Back to the Drawing Board for Fair Representation Learning
2024 · Pouget, Angéline, Jovanović, Nikola, et al. · arXiv (Cornell University)
PDF
Works count: 29
Citation count: 659
H-index: 11
I10-index: 13
Year
Topic
Type