| Inverting gradients-how easy is it to break privacy in federated learning? J Geiping, H Bauermeister, H Dröge, M Moeller Advances in neural information processing systems 33, 16937-16947, 2020 | 1438 | 2020 |
| A watermark for large language models J Kirchenbauer, J Geiping, Y Wen, J Katz, I Miers, T Goldstein Proceedings of the 40th International Conference on Machine Learning, 17061 …, 2023 | 698 | 2023 |
| A Cookbook of Self-Supervised Learning R Balestriero, M Ibrahim, V Sobal, A Morcos, S Shekhar, T Goldstein, ... arXiv preprint arXiv:2304.12210, 2023 | 467* | 2023 |
| 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 | 343* | 2023 |
| Diffusion art or digital forgery? investigating data replication in diffusion models G Somepalli, V Singla, M Goldblum, J Geiping, T Goldstein Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2023 | 331 | 2023 |
| Cold diffusion: Inverting arbitrary image transforms without noise A Bansal, E Borgnia, HM Chu, J Li, H Kazemi, F Huang, M Goldblum, ... Advances in Neural Information Processing Systems 36, 2023 | 264 | 2023 |
| Universal guidance for diffusion models A Bansal, HM Chu, A Schwarzschild, S Sengupta, M Goldblum, J Geiping, ... The Twelfth International Conference on Learning Representations, 2024 | 258* | 2024 |
| Witches' brew: Industrial scale data poisoning via gradient matching J Geiping, L Fowl, WR Huang, W Czaja, G Taylor, M Moeller, T Goldstein Ninth International Conference on Learning Representations 2021, 2021 | 249 | 2021 |
| Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery Y Wen, N Jain, J Kirchenbauer, M Goldblum, J Geiping, T Goldstein Advances in Neural Information Processing Systems 36, 2023 | 248 | 2023 |
| Metapoison: Practical general-purpose clean-label data poisoning WR Huang, J Geiping, L Fowl, G Taylor, T Goldstein Advances in Neural Information Processing Systems 33, 12080-12091, 2020 | 230 | 2020 |
| On the reliability of watermarks for large language models J Kirchenbauer, J Geiping, Y Wen, M Shu, K Saifullah, ... The Twelfth International Conference on Learning Representations, 2023 | 170* | 2023 |
| Robbing the fed: Directly obtaining private data in federated learning with modified models L Fowl, J Geiping, W Czaja, M Goldblum, T Goldstein Tenth International Conference on Learning Representations, 2022 | 158 | 2022 |
| Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images Y Wen, J Kirchenbauer, J Geiping, T Goldstein Advances in Neural Information Processing Systems 36, 2023 | 149* | 2023 |
| Strong data augmentation sanitizes poisoning and backdoor attacks without an accuracy tradeoff E Borgnia, V Cherepanova, L Fowl, A Ghiasi, J Geiping, M Goldblum, ... ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 148 | 2021 |
| Adversarial examples make strong poisons L Fowl, M Goldblum, P Chiang, J Geiping, W Czaja, T Goldstein Advances in Neural Information Processing Systems 34, 30339–30351, 2021 | 143 | 2021 |
| Understanding and mitigating copying in diffusion models G Somepalli, V Singla, M Goldblum, J Geiping, T Goldstein Advances in Neural Information Processing Systems 36, 2023 | 118 | 2023 |
| Fishing for user data in large-batch federated learning via gradient magnification Y Wen, J Geiping, L Fowl, M Goldblum, T Goldstein Proceedings of the 39th International Conference on Machine Learning, 23668 …, 2022 | 98 | 2022 |
| On the exploitability of instruction tuning M Shu, J Wang, C Zhu, J Geiping, C Xiao, T Goldstein Advances in Neural Information Processing Systems 36, 2023 | 93 | 2023 |
| 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 | 87* | 2021 |
| 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 | 86* | 2024 |
Tom GoldsteinVolpi-Cupal Professor of Computer Science, University of MarylandZweryfikowany adres z cs.umd.edu
