| On the Algorithmic Stability of Adversarial Training Y Xing, Q Song, G Cheng Neurips 2021, 2021 | 65 | 2021 |
| Diffusionshield: A watermark for copyright protection against generative diffusion models Y Cui, J Ren, H Xu, P He, H Liu, L Sun, Y Xing, J Tang arXiv preprint arXiv:2306.04642, 2023 | 59 | 2023 |
| Benefit of interpolation in nearest neighbor algorithms Y Xing, Q Song, G Cheng arXiv preprint arXiv:2202.11817, 2022 | 46* | 2022 |
| Directional Pruning of Deep Neural Networks SK Chao, Z Wang, Y Xing, G Cheng Advances in Neural Information Processing Systems 33, 2020 | 46 | 2020 |
| The good and the bad: Exploring privacy issues in retrieval-augmented generation (rag) S Zeng, J Zhang, P He, Y Xing, Y Liu, H Xu, J Ren, S Wang, D Yin, ... arXiv preprint arXiv:2402.16893, 2024 | 44 | 2024 |
| On the generalization properties of adversarial training Y Xing, Q Song, G Cheng International Conference on Artificial Intelligence and Statistics, 505-513, 2021 | 41 | 2021 |
| Adversarially robust estimate and risk analysis in linear regression Y Xing, R Zhang, G Cheng International Conference on Artificial Intelligence and Statistics, 514-522, 2021 | 30 | 2021 |
| Exploring memorization in fine-tuned language models S Zeng, Y Li, J Ren, Y Liu, H Xu, P He, Y Xing, S Wang, J Tang, D Yin arXiv preprint arXiv:2310.06714, 2023 | 19 | 2023 |
| Why Do Artificially Generated Data Help Adversarial Robustness Y Xing, Q Song, G Cheng Advances in Neural Information Processing Systems, 2022 | 17 | 2022 |
| Unveiling and mitigating memorization in text-to-image diffusion models through cross attention J Ren, Y Li, S Zeng, H Xu, L Lyu, Y Xing, J Tang European Conference on Computer Vision, 340-356, 2024 | 13 | 2024 |
| Superiority of multi-head attention in in-context linear regression Y Cui, J Ren, P He, J Tang, Y Xing arXiv preprint arXiv:2401.17426, 2024 | 13 | 2024 |
| Ft-shield: A watermark against unauthorized fine-tuning in text-to-image diffusion models Y Cui, J Ren, Y Lin, H Xu, P He, Y Xing, L Lyu, W Fan, H Liu, J Tang ACM SIGKDD Explorations Newsletter 26 (2), 76-88, 2025 | 11 | 2025 |
| Benefits of transformer: In-context learning in linear regression tasks with unstructured data Y Xing, X Lin, N Suh, Q Song, G Cheng arXiv preprint arXiv:2402.00743, 2024 | 11 | 2024 |
| Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis Y Lin, P He, H Xu, Y Xing, M Yamada, H Liu, J Tang arXiv preprint arXiv:2406.10794, 2024 | 10 | 2024 |
| Phase Transition from Clean Training to Adversarial Training Y Xing, Q Song, G Cheng Advances in Neural Information Processing Systems, 2022 | 8 | 2022 |
| Mitigating the privacy issues in retrieval-augmented generation (rag) via pure synthetic data S Zeng, J Zhang, P He, J Ren, T Zheng, H Lu, H Xu, H Liu, Y Xing, J Tang arXiv preprint arXiv:2406.14773, 2024 | 7 | 2024 |
| Data Poisoning for In-context Learning P He, H Xu, Y Xing, H Liu, M Yamada, J Tang arXiv preprint arXiv:2402.02160, 2024 | 7 | 2024 |
| Unlabeled data help: Minimax analysis and adversarial robustness Y Xing, Q Song, G Cheng International Conference on Artificial Intelligence and Statistics, 136-168, 2022 | 6 | 2022 |
| Variance Reduction for Risk Measures with Importance Sampling in Nested Simulation Y Xing, T Sit, HY Wong Quantitative Finance, 2021 | 6 | 2021 |
| Predictive power of nearest neighbors algorithm under random perturbation Y Xing, Q Song, G Cheng International Conference on Artificial Intelligence and Statistics, 496-504, 2021 | 5 | 2021 |
Qifan SongPurdue UniversityAdresse e-mail validée de purdue.edu