Vero, Mark

20 publications

ICLR 2026 Fewer Weights, More Problems: A Practical Attack on LLM Pruning Kazuki Egashira, Robin Staab, Thibaud Gloaguen, Mark Vero, Martin Vechev

ICLR 2026 Watch Your Steps: Dormant Adversarial Behaviors That Activate upon LLM Finetuning Thibaud Gloaguen, Mark Vero, Robin Staab, Martin Vechev

ICML 2025 BaxBench: Can LLMs Generate Correct and Secure Backends? Mark Vero, Niels Mündler, Victor Chibotaru, Veselin Raychev, Maximilian Baader, Nikola Jovanović, Jingxuan He, Martin Vechev

ICLRW 2025 BaxBench: Can LLMs Generate Correct and Secure Backends? Mark Vero, Niels Mündler, Victor Chibotaru, Veselin Raychev, Maximilian Baader, Nikola Jovanović, Jingxuan He, Martin Vechev

ICML 2025 Black-Box Adversarial Attacks on LLM-Based Code Completion Slobodan Jenko, Niels Mündler, Jingxuan He, Mark Vero, Martin Vechev

ICLRW 2025 Black-Box Adversarial Attacks on LLM-Based Code Completion Slobodan Jenko, Niels Mündler, Jingxuan He, Mark Vero, Martin Vechev

ICLR 2025 Language Models Are Advanced Anonymizers Robin Staab, Mark Vero, Mislav Balunovic, Martin Vechev

ICML 2025 Mind the Gap: A Practical Attack on GGUF Quantization Kazuki Egashira, Robin Staab, Mark Vero, Jingxuan He, Martin Vechev

ICLRW 2025 Mind the Gap: A Practical Attack on GGUF Quantization Kazuki Egashira, Robin Staab, Mark Vero, Jingxuan He, Martin Vechev

NeurIPS 2024 A Synthetic Dataset for Personal Attribute Inference Hanna Yukhymenko, Robin Staab, Mark Vero, Martin Vechev

ICLR 2024 Beyond Memorization: Violating Privacy via Inference with Large Language Models Robin Staab, Mark Vero, Mislav Balunovic, Martin Vechev

ICML 2024 CuTS: Customizable Tabular Synthetic Data Generation Mark Vero, Mislav Balunovic, Martin Vechev

NeurIPS 2024 Exploiting LLM Quantization Kazuki Egashira, Mark Vero, Robin Staab, Jingxuan He, Martin Vechev

ICMLW 2024 Exploiting LLM Quantization Kazuki Egashira, Mark Vero, Robin Staab, Jingxuan He, Martin Vechev

ICML 2024 Instruction Tuning for Secure Code Generation Jingxuan He, Mark Vero, Gabriela Krasnopolska, Martin Vechev

ICLRW 2024 Instruction Tuning for Secure Code Generation Jingxuan He, Mark Vero, Gabriela Krasnopolska, Martin Vechev

ICLRW 2024 Large Language Models Are Anonymizers Robin Staab, Mark Vero, Mislav Balunovic, Martin Vechev

NeurIPS 2024 Private Attribute Inference from Images with Vision-Language Models Batuhan Tömekçe, Mark Vero, Robin Staab, Martin Vechev

ICMLW 2024 Private Attribute Inference from Images with Vision-Language Models Batuhan Tömekçe, Mark Vero, Robin Staab, Martin Vechev

ICML 2023 TabLeak: Tabular Data Leakage in Federated Learning Mark Vero, Mislav Balunovic, Dimitar Iliev Dimitrov, Martin Vechev