Skip to main content

Zhuqing Liu

Title: Assistant Professor

Department: Computer Science and Engineering

College: College of Engineering

Curriculum Vitae

Curriculum Vitae Link

Education

  • PhD, Ohio State University, 2024
    Major: Electrical and Computer Engineering

Current Scheduled Teaching

No current or future courses scheduled.

Previous Scheduled Teaching

CSCE 6940.981Individual ResearchSpring 2026
CSCE 6280.002Advanced Topics in Artificial IntelligenceFall 2025 Syllabus SPOT
CSCE 6940.881Individual ResearchFall 2025
CSCE 5215.003Machine LearningFall 2025 Syllabus SPOT
CSCE 5210.002Fundamentals of Artificial IntelligenceSpring 2025 SPOT
CSCE 5210.003Fundamentals of Artificial IntelligenceSpring 2025 SPOT
CSCE 4201.002Introduction to Artificial IntelligenceSpring 2025 Syllabus SPOT

Published Intellectual Contributions

    Conference Proceeding

  • Zhang, Z., Liu, Z., Zhang, X., Chen, W., Yang, J., Liu, J. (2026). Multi-Objective Bilevel Learning. The 40th Annual AAAI Conference on Artificial Intelligence.
  • Zhang, B., Chen, Y., Fang, M., Liu, Z., Nie, L., Li, T., Liu, Z. (2026). Practical Poisoning Attacks against Retrieval-Augmented Generation. ACM Symposium on Access Control Models and Technologies.
  • Zhang, B., Xin, H., Chen, Y., Liu, Z., Yi, B., Li, T., Nie, L., Liu, Z., Fang, M. (2026). Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation. In Proc. IEEE Symposium on Security and Privacy.
  • Fang, M., Liu, Z., Zhao, X., Liu, J. (2025). Byzantine-Robust Federated Learning over Ring-All-Reduce Distributed Computing. Proceedings of the ACM Web Conference.
  • Fang, M., Nabavirazavi, S., Liu, Z., Sun, W., Iyengar, S.S., Yang, H. (2025). Do We Really Need to Design New Byzantine-robust Aggregation Rules?. Proceedings Network and Distributed System Security Symposium (NDSS). https://www.ndss-symposium.org/wp-content/uploads/2025-1796-paper.pdf
  • Qin, Z., Liu, Z., Lu, S., Liang, Y., Liu, J. (2025). DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity. The Thirteenth International Conference on Learning Representations (ICLR). The Thirteenth International Conference on Learning Representations.
  • Quan, Y., Wang, C., Zhai, S., Fang, M., Liu, Z. (2025). Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approach. in Proc. ACM MobiHoc.
  • Kasyap, H., Fang, M., Liu, Z., Maple, C., Tripathy, S. (2025). Fairness-Constrained Optimization Attack in Federated Learning". In Proc. IEEE TrustCom.
  • Wang, W., Ma, Q., Zhang, Z., Liu, Y., Liu, Z., Fang, M. (2025). Poisoning Attacks and Defenses to Federated Unlearning. Proceedings of the ACM Web Conference 2025 (WWW).
  • Cheng, Z., Sun, J., Gao, A., Quan, Y., Liu, Z., Hu, X., Fang, M. (2025). Secure Retrieval-Augmented Generation against Poisoning Attacks. IEEE BigData.
  • Liu, Z., Dong, C., Momma, M., Shao, S., Xu, S., Yang, H., Liu, J. (2025). STIMULUS: Achieving Fast Convergence and Low Sample Complexity in Stochastic Multi-Objective Learning. Conference on Uncertainty in Artificial Intelligence (UAI).
  • Dou, Z., Wang, J., Sun, W., Liu, Z., Fang, M. (2025). Toward Malicious Clients Detection in Federated Learning. In Proc. ACM AsiaCCS.
  • Zhang, B., Xin, H., Fang, M., Liu, Z., Yi, B., Li, T., Liu, Z. (2025). Traceback of Poisoning Attacks to Retrieval-Augmented Generation. In Proc. The Web Conference (WWW).
  • Liu, Z., Zhang, X., Liu, J., Zhu, Z., Lu, S. (2024). PILOT: An O (1/K)-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation. International Conference on Learning Representations.
  • Dou, Z., Hu, X., Yang, H., Liu, Z., Fang, M. (2024). Adversarial Attacks to Multi-Modal Models. LAMPS 2024 - Proceedings of the 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis. 35-46. https://api.elsevier.com/content/abstract/scopus_id/85215502541
  • Qiu, P., Li, Y., Liu, Z., Khanduri, P., Liu, J., Shroff, N.B., Bentley, E.S., Turck, K. (2023). Diamond: Taming sample and communication complexities in decentralized bilevel optimization. IEEE INFOCOM 2023-IEEE conference on computer communications. 1--10.
  • Yang, H., Liu, Z., Liu, J., Dong, C., Momma, M. (2023). Federated multi-objective learning. Other. 36 39602--39625.
  • Liu, Z., Zhang, X., Lu, S., Liu, J. (2023). Precision: Decentralized constrained min-max learning with low communication and sample complexities. Proceedings of the Twenty-fourth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing. 191--200.
  • Liu, Z., Zhang, X., Khanduri, P., Lu, S., Liu, J. (2023). Prometheus: taming sample and communication complexities in constrained decentralized stochastic bilevel learning. International Conference on Machine Learning. 22420--22453.
  • Liu, Z., Zhang, X., Khanduri, P., Lu, S., Liu, J. (2022). Interact: Achieving low sample and communication complexities in decentralized bilevel learning over networks. Proceedings of the Twenty-Third International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing. 61--70.
  • Zhang, X., Fang, M., Liu, Z., Yang, H., Liu, J., Zhu, Z. (2022). Net-fleet: Achieving linear convergence speedup for fully decentralized federated learning with heterogeneous data. Proceedings of the Twenty-Third International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing. 71--80.
  • Liu, Z., Zhang, X., Liu, J. (2022). Synthesis: A semi-asynchronous path-integrated stochastic gradient method for distributed learning in computing clusters. Proceedings of the Twenty-Third International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing. 151--160.
  • Zhang, X., Liu, Z., Liu, J., Zhu, Z., Lu, S., Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (2021). Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning. Advances in Neural Information Processing Systems. 34 18825--18838. Curran Associates, Inc.. https://proceedings.neurips.cc/paper_files/paper/2021/file/9c51a13764ca629f439f6accbb4ec413-Paper.pdf
  • Liu, Z., Duan, H., Yang, Y., Hu, X. (2016). Pendulum-like oscillation controller for UAV based on L\'evy-flight pigeon-inspired optimization and LQR. 2016 IEEE Symposium Series on Computational Intelligence (SSCI). 1--6.
  • Journal Article

  • Zhang, B., Fang, M., Liu, Z., Yi, B., Zhou, P., Wang, Y., Li, T., Liu, Z. (2026). Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning. In IEEE Transactions on Information Forensics and Security..
  • Pang, L.S., Liao, X., Zhao, C.Y., Li , C.P., Liu, Z., Ma, S. (2025). From Radioactive Effluent to Drinking Water: Efficient Removal of Trace (99)TcO(4) (-)/ReO(4) (-) by Cationic Porous Aromatic Framework.. Other. 12 (9) e2414604.
  • Yang, H., Liu, Z., Zhang, X., Liu, J. (2022). SAGDA: Achieving $$\backslash$mathcal $\$O$\$($\backslash$epsilon\^{}$\$-2$\$) $ Communication Complexity in Federated Min-Max Learning. Other. 35 7142--7154.
  • Zhang, X., Liu, Z., Liu, J., Zhu, Z., Lu, S. (2021). Taming communication and sample complexities in decentralized policy evaluation for cooperative multi-agent reinforcement learning. Other. 34 18825--18838.
  • Bi, L., Zuo, Y., Tao, F., Liao, T.W., Liu, Z. (2017). Energy-aware material selection for product with multicomponent under cloud environment. Other. 17 (3) 031007. American Society of Mechanical Engineers.
,
Overall
Summative Rating
Challenge and
Engagement Index
Response Rate

out of 5

out of 7
%
of
students responded
  • Overall Summative Rating (median):
    This rating represents the combined responses of students to the four global summative items and is presented to provide an overall index of the class’s quality. Overall summative statements include the following (response options include a Likert scale ranging from 5 = Excellent, 3 = Good, and 1= Very poor):
    • The course as a whole was
    • The course content was
    • The instructor’s contribution to the course was
    • The instructor’s effectiveness in teaching the subject matter was
  • Challenge and Engagement Index:
    This rating combines student responses to several SPOT items relating to how academically challenging students found the course to be and how engaged they were. Challenge and Engagement Index items include the following (response options include a Likert scale ranging from 7 = Much higher, 4 = Average, and 1 = Much lower):
    • Do you expect your grade in this course to be
    • The intellectual challenge presented was
    • The amount of effort you put into this course was
    • The amount of effort to succeed in this course was
    • Your involvement in course (doing assignments, attending classes, etc.) was
CLOSE