Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Mingjie Li
Observed name:
Li, Mingjie
Institution:
Helmholtz Center for Information Security
Observed institution:
Helmholtz Center for Information Security
OpenAlex ID:
A5146650141
When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
2026
·
Leng, Ye
, Chu, Junjie
, et al.
·
CISPA Helmholtz Center
Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs
2026
·
Jiang, Yukun
, Huang, Hai
, et al.
·
arXiv (Cornell University)
PDF
Finding and Reactivating Post-Trained LLMs’ Hidden Safety Mechanisms
2026
·
Li, Mingjie
, Si, Wai Man
, et al.
·
CISPA Helmholtz Center
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs
2026
·
Wai Man Si
, Mingjie Li
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data
2025
·
Atilla, Akkus
, Masound Poorghaffar, Aghdam
, et al.
·
Figshare
Show more works
View as search
Works count:
5
Citation count:
H-index:
I10-index:
Year
Topic
Type
