Zhongkui Ma

According to our database, Zhongkui Ma authored at least 10 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation.

Xinguo Feng, Zhongkui Ma, Zihan Wang, Alsharif Abuadbba, Guangdong Bai

CoRR, February, 2026

2025

Re-Key-Free, Risky-Free: Adaptable Model Usage Control.

Zihan Wang, Zhongkui Ma, Xinguo Feng, Chuan Yan, Dongge Liu, Ruoxi Sun, Derui Wang, Minhui Xue, Guangdong Bai

CoRR, November, 2025

Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization.

Zihan Wang, Zhiyong Ma, Zhongkui Ma, Shuofeng Liu, Akide Liu, Derui Wang, Minhui Xue, Guangdong Bai

CoRR, October, 2025

Convex Hull Approximation for Activation Functions.

Zhongkui Ma, Zihan Wang, Guangdong Bai

Proc. ACM Program. Lang., 2025

AI Model Modulation with Logits Redistribution.

Zihan Wang, Zhongkui Ma, Xinguo Feng, Zhiyang Mei, Ethan Ma, Derui Wang, Minhui Xue, Guangdong Bai

Proceedings of the ACM on Web Conference 2025, 2025

2024

ReLU Hull Approximation.

Zhongkui Ma, Jiaying Li, Guangdong Bai

Proc. ACM Program. Lang., January, 2024

CORELOCKER: Neuron-level Usage Control.

Zihan Wang, Zhongkui Ma, Xinguo Feng, Ruoxi Sun, Hu Wang, Minhui Xue, Guangdong Bai

Proceedings of the IEEE Symposium on Security and Privacy, 2024

Uncovering Gradient Inversion Risks in Practical Language Model Training.

Xinguo Feng, Zhongkui Ma, Zihan Wang, Eu Joe Chegne, Mengyao Ma, Alsharif Abuadbba, Guangdong Bai

Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, 2024

2023

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

Proceedings of the Formal Methods and Software Engineering, 2023

Verifying Neural Networks by Approximating Convex Hulls.

Zhongkui Ma

Proceedings of the Formal Methods and Software Engineering, 2023