Renjue Li (李仞珏)’s Homepage

Contact

  • Office: No. 601, Room 339, Building 5
  • Address: South Fourth Street 4#, Zhong Guan Cun, Beijing
  • email: lirj19###ios**ac*cn

About me

I am currently a Ph.D student in the group. My main research interests are:

  • Adversarial Attack and Defence on Neural Networks
  • Neural Network Verification

Education

  • 9/2021 – present: Ph.D. Student in Computer Software and Theory at Institute of Software, Chinese Academy of Sciences and University of Chinese Academy of Sciences
  • 9/2019 – 6/2021: Master Student in Computer Software and Theory at Institute of Software, Chinese Academy of Sciences and University of Chinese Academy of Sciences
  • 9/2015 – 6/2019: Computer Science and Technology (Bachelor’s degree) at CS, Changzhou Institute of Technology

Conferences

  • Li, R., Li, J., Huang, C. C., Yang, P., Huang, X., Zhang, L., … & Hermanns, H. (2020, November). Prodeep: a platform for robustness verification of deep neural networks. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (pp. 1630-1634).
  • Xue, B., Li, R., Zhan, N., & Fränzle, M. (2021, May). Reach-avoid Analysis for Stochastic Discrete-time Systems. In 2021 American Control Conference (ACC) (pp. 4879-4885). IEEE.
  • Yang, P., Li, R., Li, J., Huang, C. C., Wang, J., Sun, J., … & Zhang, L. (2021). Improving neural network verification through spurious region guided refinement. Tools and Algorithms for the Construction and Analysis of Systems12651, 389.

Preprints

  • Li, R., Yang, P., Huang, C. C., Xue, B., & Zhang, L. (2021). Probabilistic Robustness Analysis for DNNs based on PAC Learning. arXiv preprint arXiv:2101.10102.
  • Li, R., Zhang, H., Yang, P., Huang, C. C., Zhou, A., Xue, B., & Zhang, L. (2021). Ensemble Defense with Data Diversity: Weak Correlation Implies Strong Robustness. arXiv preprint arXiv:2106.02867.

Journal

  • Yang, P., Li, J., Liu, J., Huang, C. C., Li, R., Chen, L., … & Zhang, L. (2021). Enhancing robustness verification for deep neural networks via symbolic propagation. Formal Aspects of Computing, 1-29.