| What does it mean for a language model to preserve privacy? H Brown, K Lee, F Mireshghallah, R Shokri, F Tramèr Proceedings of the 2022 ACM conference on fairness, accountability, and …, 2022 | 266 | 2022 |
| Privacy in deep learning: A survey F Mireshghallah, M Taram, P Vepakomma, A Singh, R Raskar, ... arXiv preprint arXiv:2004.12254, 2020 | 220* | 2020 |
| Quantifying privacy risks of masked language models using membership inference attacks F Mireshghallah, K Goyal, A Uniyal, T Berg-Kirkpatrick, R Shokri arXiv preprint arXiv:2203.03929, 2022 | 167 | 2022 |
| Membership inference attacks against language models via neighbourhood comparison J Mattern, F Mireshghallah, Z Jin, B Schölkopf, M Sachan, ... arXiv preprint arXiv:2305.18462, 2023 | 166 | 2023 |
| Shredder: Learning noise distributions to protect inference privacy F Mireshghallah, M Taram, P Ramrakhyani, A Jalali, D Tullsen, ... Proceedings of the Twenty-Fifth International Conference on Architectural …, 2020 | 130* | 2020 |
| An empirical analysis of memorization in fine-tuned autoregressive language models F Mireshghallah, A Uniyal, T Wang, DK Evans, T Berg-Kirkpatrick Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022 | 124* | 2022 |
| Neither private nor fair: Impact of data imbalance on utility and fairness in differential privacy T Farrand, F Mireshghallah, S Singh, A Trask Proceedings of the 2020 workshop on privacy-preserving machine learning in …, 2020 | 123 | 2020 |
| Releq: A reinforcement learning approach for deep quantization of neural networks AT Elthakeb, P Pilligundla, FS Mireshghallah, A Yazdanbakhsh, ... arXiv preprint arXiv:1811.01704, 2018 | 118* | 2018 |
| Do membership inference attacks work on large language models? M Duan, A Suri, N Mireshghallah, S Min, W Shi, L Zettlemoyer, Y Tsvetkov, ... arXiv preprint arXiv:2402.07841, 2024 | 117* | 2024 |
| A roadmap to pluralistic alignment T Sorensen, J Moore, J Fisher, M Gordon, N Mireshghallah, CM Rytting, ... arXiv preprint arXiv:2402.05070, 2024 | 115 | 2024 |
| Can llms keep a secret? testing privacy implications of language models via contextual integrity theory N Mireshghallah*, H Kim*, X Zhou, Y Tsvetkov, M Sap, R Shokri, Y Choi arXiv preprint arXiv:2310.17884, 2023 | 77 | 2023 |
| Mix and match: Learning-free controllable text generation using energy language models F Mireshghallah, K Goyal, T Berg-Kirkpatrick arXiv preprint arXiv:2203.13299, 2022 | 77 | 2022 |
| Benchmarking differential privacy and federated learning for bert models P Basu, TS Roy, R Naidu, Z Muftuoglu, S Singh, F Mireshghallah arXiv preprint arXiv:2106.13973, 2021 | 74 | 2021 |
| Not all features are equal: Discovering essential features for preserving prediction privacy F Mireshghallah, M Taram, A Jalali, ATT Elthakeb, D Tullsen, ... Proceedings of the Web Conference 2021, 669-680, 2021 | 65* | 2021 |
| Flute: A scalable, extensible framework for high-performance federated learning simulations DD Mirian Hipolito Garcia, Andre Manoel, Daniel Madrigal Diaz, Fatemehsadat ... arXiv preprint arXiv:2203.13789, 2022 | 62* | 2022 |
| Smaller language models are better zero-shot machine-generated text detectors N Mireshghallah, J Mattern, S Gao, R Shokri, T Berg-Kirkpatrick Proceedings of the 18th Conference of the European Chapter of the …, 2024 | 57* | 2024 |
| Privacy-preserving in-context learning with differentially private few-shot generation X Tang, R Shin, HA Inan, A Manoel, F Mireshghallah, Z Lin, S Gopi, ... arXiv preprint arXiv:2309.11765, 2023 | 57 | 2023 |
| Dp-sgd vs pate: Which has less disparate impact on model accuracy? A Uniyal, R Naidu, S Kotti, S Singh, PJ Kenfack, F Mireshghallah, A Trask arXiv preprint arXiv:2106.12576, 2021 | 45 | 2021 |
| Privacy Regularization: Joint Privacy-Utility Optimization in Language Models F Mireshghallah, HA Inan, M Hasegawa, V Rühle, T Berg-Kirkpatrick, ... Proceedings of the 2021 Conference of the North American Chapter of the …, 2021 | 40 | 2021 |
| UserIdentifier: implicit user representations for simple and effective personalized sentiment analysis F Mireshghallah, V Shrivastava, M Shokouhi, T Berg-Kirkpatrick, R Sim, ... arXiv preprint arXiv:2110.00135, 2021 | 36 | 2021 |
Taylor Berg-KirkpatrickUniversity of California San DiegoVerified email at ucsd.edu
