Scholar
Zi Liang
Google Scholar ID: pzrGwvMAAAAJ
Hong Kong Polytechnic University
Natural Language Processing
AI Security
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
61
H-index
4
i10-index
2
Publications
20
Co-authors
11
list available
Publications
28 items
PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning
2026
Cited
0
SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents
2026
Cited
0
TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement
2026
Cited
0
CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?
2026
Cited
0
Where World Models Break: Natural-Input Failure Discovery
2026
Cited
0
Controlled Memory Interference in Continual LLM Agents
2026
Cited
0
Adversarial Attacks on Deep OCR Systems
2026
Cited
0
Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
2026
Cited
0
Load more
Co-authors
9 total
Haibo Hu
Professor, Hong Kong Polytechnic University
Qingqing Ye
Assistant Professor, The Hong Kong Polytechnic University
XIAO Yaxin
PhD. Student, The Hong Kong Polytechinc University
Yanyun Wang
MPhil Student, The Hong Kong University of Science and Technology (Guangzhou)
Shuo Zhang
Xi’an Jiaotong University
Sen Zhang
Hong Kong Polytechnic University
Jianliang Xu (徐建良)
IEEE Fellow; Chair Professor of Computer Science, Hong Kong Baptist University
Huadi Zheng
Unknown affiliation
