Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Shang Liu

Shang Liu

2 indexed papers

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Architecture×1Crypto×1

Frequent co-authors

Yugao Zhu1×
Zhicheng Guo1×
Mengming Li1×
Jing Wang1×
Zhiyao Xie1×
Hanyu Pei1×

Research Timeline

2026
LymphNode: A Plug-and-Play Access Control Method for Deep Neural Networks

LymphNode is a novel, post-hoc access control framework that protects Deep Neural Networks (DNNs) from model extraction and inversion attacks by enforcing a default-deny policy and selectively restoring utility only for authorized queries.

IMPart: Integration of Memetic Operations into Multi-Level Framework for Large-k-Way Hypergraph Partitioning

The paper proposes a novel memetic framework, IMPart, for k-way hypergraph partitioning that outperforms existing methods for large-k problems.

Highlighted terms show continued research focus across papers

Papers

cs.AREmpiricalRecentJun 16, 2026

IMPart: Integration of Memetic Operations into Multi-Level Framework for Large-k-Way Hypergraph Partitioning

Yugao Zhu, Zhicheng Guo, Shang Liu, Mengming Li +2 more

The paper proposes a novel memetic framework, IMPart, for k-way hypergraph partitioning that outperforms existing methods for large-k problems.

View →
cs.CRMay 15, 2026

LymphNode: A Plug-and-Play Access Control Method for Deep Neural Networks

Hanyu Pei, Shang Liu, Zeyan Liu

LymphNode is a novel, post-hoc access control framework that protects Deep Neural Networks (DNNs) from model extraction and inversion attacks by enforcing a default-deny policy and selectively restori…

View →