| Silq: A high-level quantum language with safe uncomputation and intuitive semantics B Bichsel, M Baader, T Gehr, M Vechev Proceedings of the 41st ACM SIGPLAN Conference on Programming Language …, 2020 | 145 | 2020 |
| Certifying geometric robustness of neural networks M Balunović, M Baader, G Singh, T Gehr, M Vechev Advances in Neural Information Processing Systems 32, 2019 | 127 | 2019 |
| Certified Defense to Image Transformations via Randomized Smoothing M Fischer, M Baader, M Vechev Advances in Neural Information Processing Systems 33, 2020 | 73 | 2020 |
| Scalable Certified Segmentation via Randomized Smoothing M Fischer, M Baader, M Vechev International Conference on Machine Learning, 3340-3351, 2021 | 40 | 2021 |
| Fast and precise certification of transformers G Bonaert, DI Dimitrov, M Baader, M Vechev Proceedings of the 42nd ACM SIGPLAN International Conference on Programming …, 2021 | 35 | 2021 |
| Certified defenses: Why tighter relaxations may hurt training N Jovanović, M Balunović, M Baader, M Vechev Transactions on Machine Learning Research (TMLR 10/2022), 2022 | 29* | 2022 |
| Universal approximation with certified networks M Baader, M Mirman, M Vechev International Conference on Learning Representations, 2020 | 27 | 2020 |
| Efficient Certification of Spatial Robustness A Ruoss, M Baader, M Balunović, M Vechev AAAI Conference on Artificial Intelligence 35, 2021 | 25 | 2021 |
| Latent space smoothing for individually fair representations M Peychev, A Ruoss, M Balunović, M Baader, M Vechev European Conference on Computer Vision, 535-554, 2022 | 15 | 2022 |
| The Fundamental Limits of Neural Networks for Interval Certified Robustness MB Mirman, M Baader, M Vechev Transactions on Machine Learning Research, 2022 | 9* | 2022 |
| Evading Data Contamination Detection for Language Models is (too) Easy J Dekoninck, MN Müller, M Baader, M Fischer, M Vechev arXiv preprint arXiv:2402.02823, 2024 | 8 | 2024 |
| EXPRESSIVITY OF RELU-NETWORKS UNDER CONVEX RELAXATIONS M Baader, MN Müller, Y Mao, M Vechev arXiv preprint arXiv:2311.04015, 2023 | 4 | 2023 |
| Abstraqt: Analysis of Quantum Circuits via Abstract Stabilizer Simulation B Bichsel, A Paradis, M Baader, M Vechev Quantum 7, 1185, 2023 | 3 | 2023 |
| SPEAR: Exact Gradient Inversion of Batches in Federated Learning DI Dimitrov, M Baader, MN Müller, M Vechev arXiv preprint arXiv:2403.03945, 2024 | 2 | 2024 |
| Certified Robustness to Data Poisoning in Gradient-Based Training P Sosnin, MN Müller, M Baader, C Tsay, M Wicker arXiv preprint arXiv:2406.05670, 2024 | 1 | 2024 |
| Overcoming the Paradox of Certified Training with Gaussian Smoothing S Balauca, MN Müller, Y Mao, M Baader, M Fischer, M Vechev arXiv preprint arXiv:2403.07095, 2024 | 1 | 2024 |
| Expressivity of Certified Neural Networks M Baader ETH Zurich, 2024 | | 2024 |
| DAGER: Exact Gradient Inversion for Large Language Models I Petrov, DI Dimitrov, M Baader, MN Müller, M Vechev arXiv preprint arXiv:2405.15586, 2024 | | 2024 |
| ERAN User Manual G Singh, M Balunovic, A Ruoss, C Müller, J Maurer, A Hoffmann, ... | | |
Martin VechevFull Professor of Computer Science, ETH Zurich; Scientific Director, INSAIT;在 inf.ethz.ch 的电子邮件经过验证
