| Adversarial Training and Provable Defenses: Bridging the Gap M Balunovic, M Vechev International Conference on Learning Representations, 2020 | 127 | 2020 |
| 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 | 126 | 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 | 121 | 2019 |
| 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 | 92 | 2019 |
| Learning to solve SMT formulas M Balunovic, P Bielik, M Vechev Advances in Neural Information Processing Systems, 10317-10328, 2018 | 59 | 2018 |
| Learning certified individually fair representations A Ruoss, M Balunovic, M Fischer, M Vechev Advances in neural information processing systems 33, 7584-7596, 2020 | 54 | 2020 |
| 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 | 27* | 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 | 16 | 2021 |
| Bayesian framework for gradient leakage M Balunović, DI Dimitrov, R Staab, M Vechev arXiv preprint arXiv:2111.04706, 2021 | 14 | 2021 |
| 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 | 14 | 2021 |
| Certified defenses: Why tighter relaxations may hurt training N Jovanović, M Balunović, M Baader, M Vechev arXiv e-prints, arXiv: 2102.06700, 2021 | 9 | 2021 |
| Certify or predict: Boosting certified robustness with compositional architectures MN Mueller, M Balunović, M Vechev International Conference on Learning Representations (ICLR 2021), 2021 | 6 | 2021 |
| Fair normalizing flows M Balunović, A Ruoss, M Vechev arXiv preprint arXiv:2106.05937, 2021 | 5 | 2021 |
| 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 | 4 | 2022 |
| Latent space smoothing for individually fair representations M Peychev, A Ruoss, M Balunović, M Baader, M Vechev Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel …, 2022 | 4 | 2022 |
| Learning to solve smt formulas M Balunović, P Bielik, M Vechev Advances in Neural Information Processing Systems 31, 10317-10328, 2019 | 3 | 2019 |
| Data Leakage in Federated Averaging DI Dimitrov, M Balunovic, N Konstantinov, M Vechev Transactions on Machine Learning Research, 2022 | 2 | 2022 |
| On the Paradox of Certified Training N Jovanović, M Balunović, M Baader, M Vechev arXiv preprint arXiv:2102.06700, 2021 | 1 | 2021 |
| FARE: Provably Fair Representation Learning N Jovanović, M Balunović, DI Dimitrov, M Vechev arXiv preprint arXiv:2210.07213, 2022 | | 2022 |
| Data Leakage in Tabular Federated Learning M Vero, M Balunović, DI Dimitrov, M Vechev arXiv preprint arXiv:2210.01785, 2022 | | 2022 |
Martin VechevProfessor of Computer Science, ETH ZurichVerified email at inf.ethz.ch
