Zi Liang
Scholar

Zi Liang

Google Scholar ID: pzrGwvMAAAAJ
Hong Kong Polytechnic University
Natural Language ProcessingAI Security
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
61
 
H-index
4
 
i10-index
2
 
Publications
20
 
Co-authors
11
list available
Contact
No contact links provided.
Publications
18 items
Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection
2026
Cited
0
How Vulnerable Are Edge LLMs?
2026
Cited
0
FIT: Defying Catastrophic Forgetting in Continual LLM Unlearning
2026
Cited
0
How Much Information Can a Vision Token Hold? A Scaling Law for Recognition Limits in VLMs
2026
Cited
0
From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
arXiv.org · 2026
Cited
0
Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks
2025
Cited
0
Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
2025
Cited
0
Decision Potential Surface: A Theoretical and Practical Approximation of LLM's Decision Boundary
2025
Cited
0
Resume (English only)
Co-authors
11 total
Haibo Hu
Haibo Hu
Professor, Hong Kong Polytechnic University
Qingqing Ye
Qingqing Ye
Assistant Professor, The Hong Kong Polytechnic University
XIAO Yaxin
XIAO Yaxin
PhD. Student, The Hong Kong Polytechinc University
Yanyun Wang
Yanyun Wang
MPhil Student, The Hong Kong University of Science and Technology (Guangzhou)
Shuo Zhang
Shuo Zhang
Xi’an Jiaotong University
Co-author 6
Co-author 6
Co-author 7
Co-author 7
Sen Zhang
Sen Zhang
Hong Kong Polytechnic University