| Ditto: Fair and robust federated learning through personalization T Li, S Hu, A Beirami, V Smith International conference on machine learning, 6357-6368, 2021 | 1027 | 2021 |
| A new defense against adversarial images: Turning a weakness into a strength S Hu, T Yu, C Guo, WL Chao, KQ Weinberger Advances in neural information processing systems 32, 2019 | 145 | 2019 |
| On privacy and personalization in cross-silo federated learning K Liu, S Hu, SZ Wu, V Smith Advances in neural information processing systems 35, 5925-5940, 2022 | 64 | 2022 |
| Fedsynth: Gradient compression via synthetic data in federated learning S Hu, J Goetz, K Malik, H Zhan, Z Liu, Y Liu arXiv preprint arXiv:2204.01273, 2022 | 43 | 2022 |
| Provably fair federated learning via bounded group loss S Hu, ZS Wu, V Smith arXiv preprint arXiv:2203.10190 7, 2022 | 31* | 2022 |
| Guardrail baselines for unlearning in llms P Thaker, Y Maurya, S Hu, ZS Wu, V Smith arXiv preprint arXiv:2403.03329, 2024 | 22 | 2024 |
| Private multi-task learning: Formulation and applications to federated learning S Hu, ZS Wu, V Smith arXiv preprint arXiv:2108.12978, 2021 | 19 | 2021 |
| Attacking llm watermarks by exploiting their strengths Q Pang, S Hu, W Zheng, V Smith ICLR 2024 Workshop on Secure and Trustworthy Large Language Models, 2024 | 11 | 2024 |
| Selection pressure on the rhizosphere microbiome can alter nitrogen use efficiency and seed yield in Brassica rapa J Garcia, M Gannett, LP Wei, L Cheng, S Hu, J Sparks, J Giovannoni, ... Communications Biology 5 (1), 959, 2022 | 10 | 2022 |
| Jogging the Memory of Unlearned Models Through Targeted Relearning Attacks S Hu, Y Fu, S Wu, V Smith ICML 2024 Workshop on Foundation Models in the Wild, 2024 | 8 | 2024 |
| Position: Llm unlearning benchmarks are weak measures of progress P Thaker, S Hu, N Kale, Y Maurya, ZS Wu, V Smith arXiv preprint arXiv:2410.02879, 2024 | 4 | 2024 |
| Federated Learning as a Network Effects Game S Hu, DD Ngo, S Zheng, V Smith, ZS Wu arXiv preprint arXiv:2302.08533, 2023 | 4 | 2023 |
| No free lunch in llm watermarking: Trade-offs in watermarking design choices Q Pang, S Hu, W Zheng, V Smith The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024 | 3 | 2024 |
| Privacy Amplification for the Gaussian Mechanism via Bounded Support S Hu, S Mahloujifar, V Smith, K Chaudhuri, C Guo arXiv preprint arXiv:2403.05598, 2024 | 1 | 2024 |
| Jogging the Memory of Unlearned LLMs Through Targeted Relearning Attacks S Hu, Y Fu, S Wu, V Smith Neurips Safe Generative AI Workshop 2024, 0 | | |
Virginia SmithCarnegie Mellon UniversityПодтвержден адрес электронной почты в домене cmu.edu
