Publications

Publications#

Conference Papers#

2024#

  • Uncovering Gradient Inversion Risks in Practical Language Model Training

    Xinguo Feng, Zhongkui Ma, Zihan Wang, Shuofeng Liu, Mengyao Ma, Hao Guan, Mark Huasong Meng. 2024, the 31th ACM Conference on Computer and Communications Security (CCS’24), Salt Lake City, USA. [PDF]

  • CoreLocker: Neuron-level Usage Control

    Zihan Wang, Zhongkui Ma, Xinguo Feng, Ruoxi Sun, Hu Wang, Minhui Xue, Guangdong Bai. 2024, the 45th IEEE Symposium on Security and Privacy (S&P’24), San Francisco, USA. [PDF] [GitHub] [Profile] [Live Video]

    @inproceedings{wang2024corelocker,
  title={CoreLocker: Neuron-level Usage Control},
  author={Wang, Zihan and Ma, Zhongkui and Feng, Xinguo and Sun, Ruoxi and Wang, Hu and Xue, Minhui and Bai, Guangdong},
  booktitle={2024 IEEE Symposium on Security and Privacy (SP)},
  pages={222--222},
  year={2024},
  organization={IEEE Computer Society}
}

  • ReLU Hull Approximation

    Zhongkui Ma, Jiaying Li, Guangdong Bai. 2024, the 51st ACM SIGPLAN Symposium on Principles of Programming Languages (POPL’24), London, UK. [PDF] [GitHub] [Profile] [Live Video]

    @article{ma2024relu,
  title={ReLU Hull Approximation},
  author={Ma, Zhongkui and Li, Jiaying and Bai, Guangdong},
  journal={Proceedings of the ACM on Programming Languages},
  volume={8},
  number={POPL},
  pages={2260--2287},
  year={2024},
  publisher={ACM New York, NY, USA}
}

2023#

  • Verifying Neural Networks by Approximating Convex Hulls. (Doctoral Symposium)

    Zhongkui Ma. 2023, International Conference on Formal Engineering Methods (ICFEM’23), Brisbane, Australia. [PDF]

    @inproceedings{ma2023verifying,
  title={Verifying Neural Networks by Approximating Convex Hulls},
  author={Ma, Zhongkui},
  booktitle={International Conference on Formal Engineering Methods},
  pages={261--266},
  year={2023},
  organization={Springer}
}

  • Formalizing Robustness Against Character-Level Perturbations for Neural Network Language Models

    Zhongkui Ma, Xinguo Feng, Zihan Wang, Shuofeng Liu, Mengyao Ma, Hao Guan, Mark Huasong Meng. 2023, International Conference on Formal Engineering Methods (ICFEM’23), Brisbane, Australia. [PDF] [GitHub]

    @inproceedings{ma2023formalizing,
  title={Formalizing Robustness Against Character-Level Perturbations for Neural Network Language Models},
  author={Ma, Zhongkui and Feng, Xinguo and Wang, Zihan and Liu, Shuofeng and Ma, Mengyao and Guan, Hao and Meng, Mark Huasong},
  booktitle={International Conference on Formal Engineering Methods},
  pages={100--117},
  year={2023},
  organization={Springer}
}

Journal Papers#

The following early works are about Social Simulation and Agent-based Models (ABM), supervised by Dr. Haixin Ding and published during my undergraduate period (2014-2018) and implemented by Repast Simphony.

  • Does Truthfully-Stating Strategy Really Have its Reward? — Research on the Communication Strategies of Innovation Quality (Chinese Full Text).

    Haixin Ding, Li Xie, Zhongkui Ma. 2018. Technology Intelligence Engineering. [PDF]

  • Model of Weibo Negative Public Opinion Communication in Colleges and Universities Based on Double-layer Network (Chinese Full Text).

    Zhongkui Ma. 2018. Journal of Jiamusi Vocational Institute. [PDF]

Contents