| Finding Mixed Nash Equilibria of Generative Adversarial Networks YP Hsieh, C Liu, V Cevher International Conference on Machine Learning (ICML) 2019, 2018 | 59 | 2018 |
| On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them C Liu, M Salzmann, T Lin, R Tomioka, S Süsstrunk Neural Information Processing Systems (NeurIPS) 2020, 2020 | 47 | 2020 |
| On Certifying Non-uniform Bound against Adversarial Attacks C Liu, R Tomioka, V Cevher International Conference on Machine Learning (ICML) 2019, 2019 | 21 | 2019 |
| Consistent 3D Rendering in Medical Imaging C Liu, S Miao, K Petkov, S Sudarsky, D Yu, T Mansi EP Patent EP3,373,245, 2018 | 9* | 2018 |
| Training Provably Robust Models by Polyhedral Envelope Regularization C Liu, M Salzmann, S Süsstrunk IEEE Transactions on Neural Networks and Learning Systems, 2021 | 6 | 2021 |
| Consistent 3D rendering in medical imaging K Petkov, C Liu, S Miao, S Sudarsky, D Yu, T Mansi US Patent 10,957,098, 2021 | 4 | 2021 |
| On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training C Liu, Z Huang, M Salzmann, T Zhang, S Süsstrunk arXiv preprint arXiv:2112.07324, 2021 | 3 | 2021 |
| Fast Adversarial Training with Adaptive Step Size Z Huang, Y Fan, C Liu, W Zhang, Y Zhang, M Salzmann, S Süsstrunk, ... arXiv preprint arXiv:2206.02417, 2022 | 2 | 2022 |
| Robust Binary Models by Pruning Randomly-initialized Networks C Liu, Z Zhao, S Süsstrunk, M Salzmann Neural Information Processing Systems (NeurIPS) 2022, 2022 | 1 | 2022 |
| Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks. C Liu EPFL, 2022 | | 2022 |
| Improving Adversarial Defense with Self-supervised Test-time Fine-tuning Z Huang, C Liu, M Salzmann, S Süsstrunk, T Zhang | | |
Sabine SüsstrunkProfessor, Images and Visual Representation Lab, EPFLPotvrđena adresa e-pošte na epfl.ch
