| Beyond memorization: Violating privacy via inference with large language models R Staab, M Vero, M Balunović, M Vechev International Conference on Learning Representations (ICLR 2024), 2023 | 131 | 2023 |
| Bayesian framework for gradient leakage M Balunović, DI Dimitrov, R Staab, M Vechev International Conference on Learning Representations (ICLR 2022), 2021 | 53 | 2021 |
| Watermark stealing in large language models N Jovanović, R Staab, M Vechev International Conference on Machine Learning (ICML 2024), 2024 | 30 | 2024 |
| Abstract interpretation of fixpoint iterators with applications to neural networks MN Müller, M Fischer, R Staab, M Vechev Proceedings of the ACM on Programming Languages 7 (PLDI), 786-810, 2023 | 14* | 2023 |
| Large language models are advanced anonymizers R Staab, M Vero, M Balunović, M Vechev International Conference on Learning Representations (ICLR 2025), 2024 | 12* | 2024 |
| Exploiting LLM Quantization K Egashira, M Vero, R Staab, J He, M Vechev Conference on Neural Information Processing Systems (NeurIPS 2024), 2024 | 9 | 2024 |
| COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act P Guldimann, A Spiridonov, R Staab, N Jovanović, M Vero, V Vechev, ... arXiv preprint arXiv:2410.07959, 2024 | 7 | 2024 |
| A Synthetic Dataset for Personal Attribute Inference H Yukhymenko, R Staab, M Vero, M Vechev Conference on Neural Information Processing Systems (NeurIPS 2024), 2024 | 4 | 2024 |
| Ward: Provable RAG Dataset Inference via LLM Watermarks N Jovanović, R Staab, M Baader, M Vechev International Conference on Learning Representations (ICLR 2025), 2024 | 3 | 2024 |
| From principle to practice: Vertical data minimization for machine learning R Staab, N Jovanović, M Balunović, M Vechev 2024 IEEE Symposium on Security and Privacy (SP), 4733-4752, 2024 | 3 | 2024 |
| Black-box detection of language model watermarks T Gloaguen, N Jovanović, R Staab, M Vechev International Conference on Learning Representations (ICLR 2025), 2024 | 2 | 2024 |
| Discovering Clues of Spoofed LM Watermarks T Gloaguen, N Jovanović, R Staab, M Vechev arXiv preprint arXiv:2410.02693, 2024 | 1 | 2024 |
| Private Attribute Inference from Images with Vision-Language Models B Tömekçe, M Vero, R Staab, M Vechev Conference on Neural Information Processing Systems (NeurIPS 2024), 2024 | 1 | 2024 |
| Towards Watermarking of Open-Source LLMs T Gloaguen, N Jovanović, R Staab, M Vechev arXiv preprint arXiv:2502.10525, 2025 | | 2025 |
| Back to the Drawing Board for Fair Representation Learning A Pouget, N Jovanović, M Vero, R Staab, M Vechev arXiv preprint arXiv:2405.18161, 2024 | | 2024 |
| Language Models are Advanced Anonymizers R Staab, M Vero, M Balunovic, M Vechev The Thirteenth International Conference on Learning Representations, 0 | | |
Martin VechevFull Professor of Computer Science, ETH Zurich; Scientific Director, INSAIT;ایمیل تأیید شده در inf.ethz.ch
