| Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, JB Alayrac, J Yu, R Soricut, J Schalkwyk, ... arXiv preprint arXiv:2312.11805, 2023 | 2183 | 2023 |
| PaLM 2 Technical Report R Anil, AM Dai, O Firat, M Johnson, D Lepikhin, A Passos, S Shakeri, ... Jacob Devlin, Mark Díaz, Nan Du, Ethan Dyer, Vladimir Feinberg, Fangxiaoyu …, 2023 | 1496 | 2023 |
| Machine unlearning L Bourtoule, V Chandrasekaran, CA Choquette-Choo, H Jia, A Travers, ... 42nd IEEE Symposium on Security and Privacy, 2021 | 824 | 2021 |
| Gemma: Open models based on gemini research and technology G Team, T Mesnard, C Hardin, R Dadashi, S Bhupatiraju, S Pathak, ... arXiv preprint arXiv:2403.08295, 2024 | 723 | 2024 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context G Team, P Georgiev, VI Lei, R Burnell, L Bai, A Gulati, G Tanzer, ... arXiv preprint arXiv:2403.05530, 2024 | 684 | 2024 |
| Label-Only Membership Inference Attacks CA Choquette-Choo, F Tramer, N Carlini, N Papernot 38th International Conference on Machine Learning, 2021 | 521 | 2021 |
| Entangled watermarks as a defense against model extraction H Jia, CA Choquette-Choo, V Chandrasekaran, N Papernot 30th USENIX security symposium (USENIX Security 21), 1937-1954, 2021 | 278 | 2021 |
| Are aligned neural networks adversarially aligned? N Carlini, M Nasr, CA Choquette-Choo, M Jagielski, I Gao, PWW Koh, ... Advances in Neural Information Processing Systems 36, 2024 | 237 | 2024 |
| Scalable extraction of training data from (production) language models M Nasr, N Carlini, J Hayase, M Jagielski, AF Cooper, D Ippolito, ... arXiv preprint arXiv:2311.17035, 2023 | 237 | 2023 |
| Gemma 2: Improving open language models at a practical size G Team, M Riviere, S Pathak, PG Sessa, C Hardin, S Bhupatiraju, ... arXiv preprint arXiv:2408.00118, 2024 | 192 | 2024 |
| Poisoning web-scale training datasets is practical N Carlini, M Jagielski, CA Choquette-Choo, D Paleka, W Pearce, ... 2024 IEEE Symposium on Security and Privacy (SP), 407-425, 2024 | 168 | 2024 |
| Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy D Ippolito, F Tramèr, M Nasr, C Zhang, M Jagielski, K Lee, CC Choo, ... Proceedings of the 16th International Natural Language Generation Conference …, 2023 | 131* | 2023 |
| Proof-of-Learning: Definitions and Practice H Jia, M Yaghini, CA Choquette-Choo, N Dullerud, A Thudi, ... 42nd IEEE Symposium on Security and Privacy, 2021 | 103 | 2021 |
| Madlad-400: A multilingual and document-level large audited dataset S Kudugunta, I Caswell, B Zhang, X Garcia, CA Choquette-Choo, K Lee, ... Advances in Neural Information Processing Systems 36, 2024 | 77 | 2024 |
| Federated learning of gboard language models with differential privacy Z Xu, Y Zhang, G Andrew, CA Choquette-Choo, P Kairouz, HB McMahan, ... arXiv preprint arXiv:2305.18465, 2023 | 75 | 2023 |
| CaPC Learning: Confidential and Private Collaborative Learning CA Choquette-Choo, N Dullerud, A Dziedzic, Y Zhang, S Jha, N Papernot, ... 9th International Conference on Learning Representations, 2021 | 67 | 2021 |
| The fundamental price of secure aggregation in differentially private federated learning WN Chen, CAC Choo, P Kairouz, AT Suresh International Conference on Machine Learning, 3056-3089, 2022 | 65 | 2022 |
| PaLM 2 Technical Report; 2023 R Anil, AM Dai, O Firat, M Johnson, D Lepikhin, A Passos, S Shakeri, ... arXiv preprint arXiv:2305.10403, 2023 | 51 | 2023 |
| PaLM 2 Technical Report CA Cherry Aakanksha, 0 | 43* | |
| Codegemma: Open code models based on gemma CG Team, AJ Hartman, A Hu, CA Choquette-Choo, H Zhao, J Fine, J Hui, ... URL https://storage. googleapis. com/deepmind-media/gemma/codegemma_report. pdf, 0 | 40* | |
Nicolas PapernotUniversity of Toronto and Vector InstituteVerified email at utoronto.ca
