Yun Shen
Scholar

Yun Shen

Google Scholar ID: Gx_JJ6cAAAAJ
Flexera
AI/ML for SecurityAI/ML SafetyCloud Computing
Google Scholar↗
Citations & Impact
All-time
Citations
3,066
 
H-index
25
 
i10-index
45
 
Publications
20
 
Co-authors
44
list available
Contact
No contact links provided.
Publications
12 items
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
2026
Cited
0
When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
2026
Cited
0
Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks
2026
Cited
0
DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning
2026
Cited
0
Video Object Recognition in Mobile Edge Networks: Local Tracking or Edge Detection?
2025
Cited
0
"To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios
2025
Cited
0
JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring
2025
Cited
0
When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs
2025
Cited
0
Resume (English only)
Co-authors
44 total
Yang Zhang
Yang Zhang
Faculty at CISPA Helmholtz Center for Information Security
Michael Backes
Michael Backes
Chairman and Founding Director of the CISPA Helmholtz Center for Information Security
Han Yufei
Han Yufei
INRIA
Co-author 4
Co-author 4
Xinyue Shen
Xinyue Shen
CISPA Helmholtz Center for Information Security
Gianluca Stringhini
Gianluca Stringhini
Associate Professor at Boston University
Co-author 7
Co-author 7
Xinlei He
Xinlei He
Assistant Professor, HKUST(GZ)