| Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses M Goldblum, D Tsipras, C Xie, X Chen, A Schwarzschild, D Song, ... IEEE Transactions on Pattern Analysis and Machine Intelligence 45 (2), 1563-1580, 2022 | 341* | 2022 |
| 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 | 330* | 2021 |
| Baseline defenses for adversarial attacks against aligned language models N Jain, A Schwarzschild, Y Wen, G Somepalli, J Kirchenbauer, P Chiang, ... arXiv preprint arXiv:2309.00614, 2023 | 251* | 2023 |
| Universal guidance for diffusion models A Bansal, HM Chu, A Schwarzschild, S Sengupta, M Goldblum, J Geiping, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 196* | 2023 |
| 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, 2020 | 185 | 2020 |
| A Cookbook of Self-Supervised Learning,(2023) R Balestriero, M Ibrahim, V Sobal, A Morcos, S Shekhar, T Goldstein, ... arXiv preprint arXiv:2304.12210, 0 | 100* | |
| Tofu: A task of fictitious unlearning for llms P Maini, Z Feng, A Schwarzschild, ZC Lipton, JZ Kolter arXiv preprint arXiv:2401.06121, 2024 | 92* | 2024 |
| Transfer learning with deep tabular models R Levin, V Cherepanova, A Schwarzschild, A Bansal, CB Bruss, ... arXiv preprint arXiv:2206.15306, 2022 | 72* | 2022 |
| Can you learn an algorithm? generalizing from easy to hard problems with recurrent networks A Schwarzschild, E Borgnia, A Gupta, F Huang, U Vishkin, M Goldblum, ... Advances in Neural Information Processing Systems 34, 6695-6706, 2021 | 72 | 2021 |
| Neftune: Noisy embeddings improve instruction finetuning N Jain, P Chiang, Y Wen, J Kirchenbauer, HM Chu, G Somepalli, ... arXiv preprint arXiv:2310.05914, 2023 | 63* | 2023 |
| 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, 2019 | 44* | 2019 |
| Spotting llms with binoculars: Zero-shot detection of machine-generated text A Hans, A Schwarzschild, V Cherepanova, H Kazemi, A Saha, ... arXiv preprint arXiv:2401.12070, 2024 | 42* | 2024 |
| End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking A Bansal, A Schwarzschild, E Borgnia, Z Emam, F Huang, M Goldblum, ... 36th Conference on Neural Information Processing Systems (NeurIPS 2022), 2022 | 41* | 2022 |
| Adversarial attacks on machine learning systems for high-frequency trading M Goldblum, A Schwarzschild, A Patel, T Goldstein Proceedings of the Second ACM International Conference on AI in Finance, 1-9, 2021 | 34* | 2021 |
| Transformers Can Do Arithmetic with the Right Embeddings S McLeish, A Bansal, A Stein, N Jain, J Kirchenbauer, BR Bartoldson, ... arXiv preprint arXiv:2405.17399, 2024 | 18* | 2024 |
| Rethinking llm memorization through the lens of adversarial compression A Schwarzschild, Z Feng, P Maini, ZC Lipton, JZ Kolter arXiv preprint arXiv:2404.15146, 2024 | 18 | 2024 |
| Saint: Improved neural networks for tabular data via row attention and contrastive pre-training. arXiv G Somepalli, M Goldblum, A Schwarzschild, CB Bruss, T Goldstein arXiv preprint arXiv:2106.01342, 2021 | 12 | 2021 |
| The Uncanny Similarity of Recurrence and Depth A Schwarzschild, A Gupta, M Goldblum, T Goldstein International Conference on Learning Representations (ICLR) 2022, 2022 | 10 | 2022 |
| Datasets for studying generalization from easy to hard examples A Schwarzschild, E Borgnia, A Gupta, A Bansal, Z Emam, F Huang, ... arXiv preprint arXiv:2108.06011, 2021 | 10 | 2021 |
| MetaBalance: high-performance neural networks for class-imbalanced data A Bansal, M Goldblum, V Cherepanova, A Schwarzschild, CB Bruss, ... arXiv preprint arXiv:2106.09643, 2021 | 9 | 2021 |
Micah GoldblumColumbia UniversityAdresse e-mail validée de columbia.edu