Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Zesen Liu
Observed name:
Liu, Zesen
Institution:
Hong Kong University of Science and Technology
Observed institutions:
Xidian University,
Hong Kong University of Science and Technology,
The Hong Kong University of Science and Technology (Guangzhou)
ORCID:
0009-0007-0776-8839
Observed ORCID:
0009-0007-0776-8839
OpenAlex ID:
A5104347529
Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
2026
·
Yuchong Xie
, Mingyu Luo
, et al.
·
Proceedings of the ACM on software engineering.
·
14
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
2026
·
Zhang, Zhixiang
, Liu, Zesen
, et al.
·
arXiv (Cornell University)
·
6
PDF
On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks
2024
·
Liu, Zesen
, Cong, Tianshuo
, et al.
·
arXiv (Cornell University)
·
6
PDF
Rewriting the Response Path: Silent Tampering and Provider-Signed Defense in BYOK LLM Agents
2026
·
Luo, Mingyu
, Zhang, Zihan
, et al.
·
arXiv (Cornell University)
·
3
PDF
Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents
2026
·
Liu, Zesen
, Zhang, Zihan
, et al.
·
arXiv (Cornell University)
·
2
PDF
Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery
2026
·
Zhang, Kaikai
, Zhang, Zihan
, et al.
·
arXiv (Cornell University)
·
1
PDF
Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
2026
·
Zhang, Zihan
, Yao, Shuangjie
, et al.
·
arXiv (Cornell University)
·
1
PDF
Show more works
View as search
Works count:
9
Citation count:
41
H-index:
4
I10-index:
1
Year
Topic
Type
