Robin Staab

According to our database, Robin Staab authored at least 22 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Mind the Gap: A Practical Attack on GGUF Quantization.

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

CoRR, May, 2025

MixAT: Combining Continuous and Discrete Adversarial Training for LLMs.

Csaba Dékány, Stefan Balauca, Robin Staab, Dimitar I. Dimitrov, Martin T. Vechev

CoRR, May, 2025

Robust LLM Fingerprinting via Domain-Specific Watermarks.

Thibaud Gloaguen, Robin Staab, Nikola Jovanovic, Martin T. Vechev

CoRR, May, 2025

Finetuning-Activated Backdoors in LLMs.

Thibaud Gloaguen, Mark Vero, Robin Staab, Martin T. Vechev

CoRR, May, 2025

Towards Watermarking of Open-Source LLMs.

Thibaud Gloaguen, Nikola Jovanovic, Robin Staab, Martin T. Vechev

CoRR, February, 2025

Language Models are Advanced Anonymizers.

Robin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Black-Box Detection of Language Model Watermarks.

Thibaud Gloaguen, Nikola Jovanovic, Robin Staab, Martin T. Vechev

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Ward: Provable RAG Dataset Inference via LLM Watermarks.

Nikola Jovanovic, Robin Staab, Maximilian Baader, Martin T. Vechev

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

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

Philipp Guldimann, Alexander Spiridonov, Robin Staab, Nikola Jovanovic, Mark Vero, Velko Vechev, Anna Gueorguieva, Mislav Balunovic, Nikola Konstantinov, Pavol Bielik, Petar Tsankov, Martin T. Vechev

CoRR, 2024

Discovering Clues of Spoofed LM Watermarks.

Thibaud Gloaguen, Nikola Jovanovic, Robin Staab, Martin T. Vechev

CoRR, 2024

Back to the Drawing Board for Fair Representation Learning.

Angéline Pouget, Nikola Jovanovic, Mark Vero, Robin Staab, Martin T. Vechev

CoRR, 2024

Large Language Models are Advanced Anonymizers.

Robin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev

CoRR, 2024

From Principle to Practice: Vertical Data Minimization for Machine Learning.

Robin Staab, Nikola Jovanovic, Mislav Balunovic, Martin T. Vechev

Proceedings of the IEEE Symposium on Security and Privacy, 2024

A Synthetic Dataset for Personal Attribute Inference.

Hanna Yukhymenko, Robin Staab, Mark Vero, Martin T. Vechev

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Private Attribute Inference from Images with Vision-Language Models.

Batuhan Tömekçe, Mark Vero, Robin Staab, Martin T. Vechev

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Exploiting LLM Quantization.

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

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Watermark Stealing in Large Language Models.

Nikola Jovanovic, Robin Staab, Martin T. Vechev

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Beyond Memorization: Violating Privacy via Inference with Large Language Models.

Robin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks - Artifact.

Mark Niklas Müller, Marc Fischer, Robin Staab, Martin T. Vechev

Dataset, June, 2023

Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks.

Mark Niklas Müller, Marc Fischer, Robin Staab, Martin T. Vechev

Proc. ACM Program. Lang., 2023

2022

Bayesian Framework for Gradient Leakage.

Mislav Balunovic, Dimitar Iliev Dimitrov, Robin Staab, Martin T. Vechev

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Effective Certification of Monotone Deep Equilibrium Models.

Mark Niklas Müller, Robin Staab, Marc Fischer, Martin T. Vechev

CoRR, 2021