2026 AAAI EASE: Practical and Efficient Safety Alignment for Small Language Models Haonan Shi, Guoli Wang, Tu Ouyang, and 1 more author In The 40th Annual AAAI Conference on Artificial Intelligence (AAAI)(oral), 2026 arXiv PDF 2025 WWW Navigating the Designs of Privacy-Preserving Fine-tuning for Large Language Models Haonan Shi, Tu Ouyang, and An Wang In International World Wide Web Conference (WWW), 2025 DOI arXiv PDF PoPETs Unveiling Client Privacy Leakage from Public Dataset Usage in Federated Distillation Haonan Shi, Tu Ouyang, and An Wang In Proceedings on Privacy Enhancing Technologies Symposium (PoPETs), 2025 DOI arXiv PDF 2024 EuroS&P Learning-Based Difficulty Calibration for Enhanced Membership Inference Attacks Haonan Shi, Tu Ouyang, and An Wang In IEEE 9th European Symposium on Security and Privacy (EuroS&P), 2024 DOI arXiv PDF 2023 Arxiv A Trajectory K-Anonymity Model Based on Point Density and Partition Wanshu Yu*, Haonan Shi*, and Hongyun Xu In Arxiv, 2023 * Equal contribution. arXiv PDF
