| Lipschitz-certifiable training with a tight outer bound S Lee, J Lee, S Park NeurIPS 2020, 2020 | 47 | 2020 |
| Graddiv: Adversarial robustness of randomized neural networks via gradient diversity regularization S Lee, H Kim, J Lee IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 | 38 | 2022 |
| Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples S Lee, W Lee, J Park, J Lee NeurIPS 2021, 2021 | 24 | 2021 |
| A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution S Lee, C Jang ICLR 2023, 2023 | 8 | 2023 |
| A Reparametrization-Invariant Sharpness Measure Based on Information Geometry C Jang, S Lee, FC Park, YK Noh NeurIPS 2022, 2022 | 6 | 2022 |
| Bridged adversarial training H Kim, W Lee, S Lee, J Lee Neural Networks 167, 266-282, 2023 | 5 | 2023 |
| Implicit Jacobian regularization weighted with impurity of probability output S Lee, J Park, J Lee ICML 2023, 2023 | 5* | 2023 |
| Defensive denoising methods against adversarial attack S Lee, S Park, J Lee KDD 2018 Deep Learning Day, 2018 | 5 | 2018 |
| Variational cycle-consistent imputation adversarial networks for general missing patterns W Lee, S Lee, J Byun, H Kim, J Lee Pattern Recognition, 2022 | 4 | 2022 |
| Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors S Lee, S Lee arXiv preprint arXiv:2305.12883, 2023 | 2* | 2023 |
Jaewook LeeProfessor of Industrial Engineering, Seoul National Universitysnu.ac.kr의 이메일 확인됨
