Shengfang Zhai
Scholar

Shengfang Zhai

Google Scholar ID: bJYY-tIAAAAJ
Peking University
Trustworthy AIGenerative ModelsAI PrivacyBackdoor Attacks
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
283
 
H-index
7
 
i10-index
7
 
Publications
17
 
Co-authors
13
list available
Contact
No contact links provided.
Publications
10 items
Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch
2026
Cited
0
IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation
2026
Cited
0
MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
2026
Cited
0
DMark: Order-Agnostic Watermarking for Diffusion Large Language Models
2025
Cited
0
Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries
2025
Cited
0
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
2025
Cited
0
Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
2025
Cited
0
NaviDet: Efficient Input-level Backdoor Detection on Text-to-Image Synthesis via Neuron Activation Variation
2025
Cited
0
Resume (English only)
Co-authors
13 total
qingni shen
qingni shen
Peking University
Yinpeng Dong
Yinpeng Dong
Tsinghua University
Jiaheng Zhang
Jiaheng Zhang
Assistant Professor, National University of Singapore.
Hang Su
Hang Su
Associated Professor, Tsinghua University
Xiaoyi Chen
Xiaoyi Chen
Indiana University Bloomington
Yue Liu
Yue Liu
National University of Singapore
Shi Pu
Shi Pu
贵州电信 China Telecom Guizhou Branch
Yansong (Garrison) Gao
Yansong (Garrison) Gao
The University of Western Australia