| Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses M Goldblum, D Tsipras, C Xie, ... IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022, 2022 | 139* | 2022 |
| Adversarially Robust Distillation M Goldblum, L Fowl, S Feizi, T Goldstein AAAI Conference on Artificial Intelligence (AAAI) 2020, 2020 | 110 | 2020 |
| The Intrinsic Dimension of Images and Its Impact on Learning P Pope, C Zhu, A Abdelkader, M Goldblum, T Goldstein International Conference on Learning Representations (ICLR) 2021, 2021 | 96 | 2021 |
| Just how toxic is data poisoning? a unified benchmark for backdoor and data poisoning attacks A Schwarzschild*, M Goldblum*, A Gupta, JP Dickerson, T Goldstein International Conference on Machine Learning (ICML) 2021, 2021 | 92 | 2021 |
| Saint: Improved neural networks for tabular data via row attention and contrastive pre-training G Somepalli, M Goldblum, A Schwarzschild, CB Bruss, T Goldstein arXiv preprint arXiv:2106.01342, 2021 | 88* | 2021 |
| Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff E Borgnia, V Cherepanova, L Fowl, A Ghiasi, J Geiping, M Goldblum, ... International Conference on Acoustics, Speech, and Signal Processing (ICASSP …, 2021 | 76* | 2021 |
| LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition V Cherepanova, M Goldblum, H Foley, S Duan, J Dickerson, G Taylor, ... International Conference on Learning Representations (ICLR) 2021, 2021 | 66 | 2021 |
| Data Augmentation for Meta-Learning R Ni, M Goldblum, A Sharaf, K Kong, T Goldstein International Conference on Machine Learning (ICML) 2021, 2021 | 64* | 2021 |
| Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks M Goldblum, S Reich, L Fowl, R Ni, V Cherepanova, T Goldstein International Conference on Machine Learning (ICML) 2020, 2020 | 61 | 2020 |
| Adversarially Robust Few-Shot Learning: A Meta-Learning Approach M Goldblum, L Fowl, T Goldstein Advances in Neural Information Processing Systems (NeurIPS), 2020 | 59* | 2020 |
| Cold diffusion: Inverting arbitrary image transforms without noise A Bansal, E Borgnia, HM Chu, JS Li, H Kazemi, F Huang, M Goldblum, ... arXiv preprint arXiv:2208.09392, 2022 | 52 | 2022 |
| Adversarial Examples Make Strong Poisons L Fowl*, M Goldblum*, P Chiang, J Geiping, W Czaja, T Goldstein Advances in Neural Information Processing Systems (NeurIPS), 2021 | 51 | 2021 |
| Understanding generalization through visualizations WR Huang, Z Emam, M Goldblum, L Fowl, JK Terry, F Huang, T Goldstein NeurIPS 2020 ICBINB Workshop, 2020 | 47 | 2020 |
| Stochastic training is not necessary for generalization J Geiping, M Goldblum, PE Pope, M Moeller, T Goldstein International Conference on Learning Representations (ICLR) 2022, 2022 | 39 | 2022 |
| What Doesn't Kill You Makes You Robust (er): Adversarial Training against Poisons and Backdoors J Geiping, L Fowl, G Somepalli, M Goldblum, M Moeller, T Goldstein ICLR 2021 Workshop on Security and Safety in Machine Learning Systems, 2021 | 39* | 2021 |
| Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models L Fowl, J Geiping, W Czaja, M Goldblum, T Goldstein International Conference on Learning Representations (ICLR) 2022, 2022 | 36 | 2022 |
| Sleeper agent: Scalable hidden trigger backdoors for neural networks trained from scratch H Souri, L Fowl, R Chellappa, M Goldblum, T Goldstein Advances in Neural Information Processing Systems (NeurIPS), 2022 | 33 | 2022 |
| Towards transferable adversarial attacks on vision transformers Z Wei, J Chen, M Goldblum, Z Wu, T Goldstein, YG Jiang Proceedings of the AAAI Conference on Artificial Intelligence 36 (3), 2668-2676, 2022 | 32 | 2022 |
| Can You Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective G Somepalli, L Fowl, A Bansal, P Yeh-Chiang, Y Dar, R Baraniuk, ... Conference on Computer Vision and Pattern Recognition (CVPR) 2022, 2022 | 31* | 2022 |
| Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory M Goldblum, J Geiping, A Schwarzschild, M Moeller, T Goldstein International Conference on Learning Representations (ICLR) 2020, 2020 | 31 | 2020 |
Tom GoldsteinVolpi-Cupal Associate Professor of Computer Science, University of MarylandVerified email at cs.umd.edu
