| Learning to fuzz from symbolic execution with application to smart contracts J He, M Balunović, N Ambroladze, P Tsankov, M Vechev Proceedings of the 2019 ACM SIGSAC conference on computer and communications …, 2019 | 289 | 2019 |
| DL2: Training and Querying Neural Networks with Logic M Fischer, M Balunovic, D Drachsler-Cohen, T Gehr, C Zhang, M Vechev International Conference on Machine Learning, 1931-1941, 2019 | 221 | 2019 |
| Adversarial Training and Provable Defenses: Bridging the Gap M Balunovic, M Vechev International Conference on Learning Representations, 2020 | 198 | 2020 |
| Certifying Geometric Robustness of Neural Networks M Balunovic, M Baader, G Singh, T Gehr, M Vechev Advances in Neural Information Processing Systems, 15287-15297, 2019 | 148 | 2019 |
| Beyond memorization: Violating privacy via inference with large language models R Staab, M Vero, M Balunović, M Vechev arXiv preprint arXiv:2310.07298, 2023 | 141 | 2023 |
| Learning certified individually fair representations A Ruoss, M Balunovic, M Fischer, M Vechev Advances in neural information processing systems 33, 7584-7596, 2020 | 113 | 2020 |
| Learning to solve SMT formulas M Balunovic, P Bielik, M Vechev Advances in Neural Information Processing Systems, 10317-10328, 2018 | 88 | 2018 |
| Lamp: Extracting text from gradients with language model priors M Balunovic, D Dimitrov, N Jovanović, M Vechev Advances in Neural Information Processing Systems 35, 7641-7654, 2022 | 72* | 2022 |
| Scalable polyhedral verification of recurrent neural networks W Ryou, J Chen, M Balunovic, G Singh, A Dan, M Vechev Computer Aided Verification: 33rd International Conference, CAV 2021 …, 2021 | 55* | 2021 |
| Bayesian framework for gradient leakage M Balunović, DI Dimitrov, R Staab, M Vechev arXiv preprint arXiv:2111.04706, 2021 | 54 | 2021 |
| Fair normalizing flows M Balunović, A Ruoss, M Vechev arXiv preprint arXiv:2106.05937, 2021 | 43 | 2021 |
| On the paradox of certified training N Jovanović, M Balunović, M Baader, M Vechev arXiv preprint arXiv:2102.06700, 2021 | 34* | 2021 |
| Data leakage in federated averaging DI Dimitrov, M Balunovic, N Konstantinov, M Vechev Transactions on Machine Learning Research, 2022 | 32 | 2022 |
| Efficient certification of spatial robustness A Ruoss, M Baader, M Balunović, M Vechev Proceedings of the AAAI conference on artificial intelligence 35 (3), 2504-2513, 2021 | 30 | 2021 |
| Robustness certification for point cloud models T Lorenz, A Ruoss, M Balunović, G Singh, M Vechev Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 30 | 2021 |
| AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents E Debenedetti, J Zhang, M Balunovic, L Beurer-Kellner, M Fischer, ... The Thirty-eight Conference on Neural Information Processing Systems …, 2024 | 29* | 2024 |
| TabLeak: Tabular data leakage in federated learning M Vero, M Balunović, DI Dimitrov, M Vechev arXiv preprint arXiv:2210.01785, 2022 | 21* | 2022 |
| 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 | 18 | 2022 |
| Certify or predict: Boosting certified robustness with compositional architectures MN Müller, M Balunović, M Vechev International Conference on Learning Representations (ICLR 2021), 2021 | 15 | 2021 |
| Large language models are advanced anonymizers R Staab, M Vero, M Balunović, M Vechev arXiv preprint arXiv:2402.13846, 2024 | 13* | 2024 |
Martin VechevFull Professor of Computer Science, ETH Zurich; Scientific Director, INSAIT;Verified email at inf.ethz.ch
