Prof. LIU Chen (劉晨)
Research Output
- 2024
- Published
Towards Efficient Training and Evaluation of Robust Models against l0 Bounded Adversarial Perturbations
Zhong, X., Huang, Y. & Liu, C., 2024, Proceedings of the 41st International Conference on Machine Learning.Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
- 2023
Training Provably Robust Models by Polyhedral Envelope Regularization
Liu, C., Salzmann, M. & Süsstrunk, S., Jun 2023, In: IEEE Transactions on Neural Networks and Learning Systems. 34, 6, p. 3146-3160Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Scopus citations: 3- Published
Fast adversarial training with adaptive step size
Huang, Z., Fan, Y., Liu, C., Zhang, W., Zhang, Y., Salzmann, M., Süsstrunk, S., & 1 others , 2023, In: IEEE Transactions on Image Processing. 32, p. 6102-6114 13 p.Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Scopus citations: 3 - Published
Towards Stable and Efficient Adversarial Training against l1 Bounded Adversarial Attacks
Jiang, Y., Liu, C., Huang, Z., Salzmann, M. & Süsstrunk, S., 2023, Proceedings of the 40th International Conference on Machine Learning. Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S. & Scarlett, J. (eds.). p. 15089-15104 16 p. 615. (Proceedings of Machine Learning Research; vol. 202).Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Scopus citations: 3 - 2022
- Published
Robust Binary Models by Pruning Randomly-initialized Networks
Liu, C., Zhao, Z., Süsstrunk, S. & Salzmann, M., Nov 2022, Thirty-Sixth Conference on Neural Information Processing Systems, NeurIPS 2022. Neural Information Processing Systems (NeurIPS), 15 p. (Advances in Neural Information Processing Systems; vol. 35).Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks
LIU, C., 2022, Lausanne: Ecole Polytechnique Federale de Lausanne (EPFL).Research output: Faculty's Theses › Doctoral thesis
- 2020
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them
Liu, C., Salzmann, M., Lin, T., Tomioka, R. & Süsstrunk, S., Dec 2020, NeurIPS Proceedings: Advances in Neural Information Processing Systems 33 (NeurIPS 2020). Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M. & Lin, H. (eds.). Vol. 33.Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Scopus citations: 35- 2019
Finding Mixed Nash Equilibria of Generative Adversarial Networks
Hsieh, Y., Liu, C. & Cevher, V., Jun 2019, 36th International Conference on Machine Learning (ICML 2019) . Chaudhur, K. & Salakhutdinov, R. (eds.). International Machine Learning Society (IMLS), p. 4972-5000 (Proceedings of Machine Learning Research; vol. 97).Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Scopus citations: 14On Certifying Non-uniform Bound against Adversarial Attacks
Liu, C., Tomioka, R. & Cevher, V., Jun 2019, Proceedings of the 36th International Conference on Machine Learning, ICML 2019. Chaudhuri, K. & Salakhutdinov, R. (eds.). International Conference on Machine Learning (ICML), p. 4072-4081 (Proceedings of Machine Learning Research; vol. 97).Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Scopus citations: 10