Publications

@article{he2026defending,
    title={Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment},
    author={He, Lipeng and Wang, Yihan and Zhang, Jiawen and Asokan, N.},
    journal={arXiv preprint arXiv:2606.15441},
    year={2026}
}

@article{sanderson2026sequential,
    title={Sequential Data Poisoning in LLM Post-Training},
    author={Sanderson, Jack and Wang, Yihan and Lu, Xiaoqian and Kamath, Gautam and Lu, Yiwei},
    journal={arXiv preprint arXiv:2606.04929},
    year={2026}
}

@article{xu2025targeted,
    title={Are Targeted Data Poisoning Attacks as Effective as We Think?},
    author={Xu, William and Zhang, Chenyu and Wang, Yihan and Yang, Matthew Y.R. and Liu, Zuoqiu and Yu, Yaoliang and Kamath, Gautam and Lu, Yiwei},
    journal={arXiv preprint arXiv:2509.06896},
    year={2025}
}

@inproceedings{wang2026extracting,
    title={Extracting Training Data from Diffusion Language Models via Infilling},
    author={Wang, Yihan and Asokan, N.},
    booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
    year={2026}
}

@inproceedings{zhu2026towards,
    title={Towards Robust Content Watermarking Against Removal and Forgery Attacks},
    author={Zhu, Yifan and Wang, Yihan and Gao, Xiao-Shan},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings},
    year={2026}
}

@inproceedings{liao2026cross,
    title={Cross-Session Decomposition Attacks: Scaling Risk and Intent-Aligned Retrieval Defense},
    author={Liao, Disen and Wang, Yihan and Shi, Freda and Yu, Yaoliang},
    booktitle={Findings of the Association for Computational Linguistics: EMNLP 2026},
    year={2026}
}

@inproceedings{wang2025bridgepure,
    title={BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection},
    author={Wang, Yihan and Lu, Yiwei and Gao, Xiao-Shan and Kamath, Gautam and Yu, Yaoliang},
    booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
    year={2025}
}

@inproceedings{liu2025provable,
    title={Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization},
    author={Liu, Shuang and Wang, Yihan and Zhu, Yifan and Miao, Yibo and Gao, Xiao-Shan},
    booktitle={The Thirteenth International Conference on Learning Representations (ICLR)},
    year={2025}
}

@article{wangMUCMachineUnlearning,
  title = {{{MUC}}: {{Machine Unlearning}} for {{Contrastive Learning}} with {{Black-box Evaluation}}},
  author = {Wang, Yihan and Lu, Yiwei and Zhang, Guojun and Boenisch, Franziska and Dziedzic, Adam and Yu, Yaoliang and Gao, Xiao-Shan},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2025}
}

@article{wang2025data,
    title={Data-dependent Stability Analysis of Adversarial Training},
    author={Wang, Yihan and Liu, Shuang and Gao, Xiao-Shan},
    journal={Neural Networks},
    volume={183},
    pages={106983},
    year={2025},
    doi={10.1016/j.neunet.2024.106983}
}

@inproceedings{wang2024efficient,
    title={Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously},
    author={Wang, Yihan and Zhu, Yifan and Gao, Xiao-Shan},
    booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
    year={2024}
}

@article{LWG24,
    title={Game-Theoretic Unlearnable Example Generator},
    volume={38},
    url={https://ojs.aaai.org/index.php/AAAI/article/view/30130},
    DOI={10.1609/aaai.v38i19.30130},
    author={Liu, Shuang and Wang, Yihan and Gao, Xiao-Shan}, year={2024}, month={Mar.},
    pages={21349-21358}
}

@inproceedings{
    LWZY24,
    title={On the Robustness of Neural Networks Quantization against Data Poisoning Attacks},
    author={Yiwei Lu and Yihan Wang and Guojun Zhang and Yaoliang Yu},
    booktitle={ICML 2024 Next Generation of AI Safety Workshop},
    year={2024},
    url={https://openreview.net/forum?id=YuXWnkhZOj}
    }

@InProceedings{YWG23,
title = 	 {Adversarial Parameter Attack on Deep Neural Networks},
author =       {Yu, Lijia and Wang, Yihan and Gao, Xiao-Shan},
booktitle = 	 {Proceedings of the 40th International Conference on Machine Learning},
pages = 	 {40354--40372},
year = 	 {2023},
editor = 	 {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan},
volume = 	 {202},
series = 	 {Proceedings of Machine Learning Research},
month = 	 {23--29 Jul},
publisher =    {PMLR},
url = 	 {https://proceedings.mlr.press/v202/yu23f.html},
}

@InProceedings{10.1007/978-981-99-8132-8_44,
    author="Wang, Yihan
    and Yu, Lijia
    and Gao, Xiao-Shan",
    editor="Luo, Biao
    and Cheng, Long
    and Wu, Zheng-Guang
    and Li, Hongyi
    and Li, Chaojie",
    title="Restore Translation Using Equivariant Neural Networks",
    booktitle="Neural Information Processing",
    year="2024",
    publisher="Springer Nature Singapore",
    address="Singapore",
    pages="583--603",
    isbn="978-981-99-8132-8"
    }