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

Ziyang Li

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2Prog. Lang.×1Software Eng.×1AI×1

Frequent co-authors

Jie Zhu1×
Penghui Li1×
Zhongxuan Li1×
Chihao Shen1×
Yizheng Chen1×
Kexin Pei1×

Research Timeline

2026
Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs

The paper proposes a commit-open protocol using SAE feature-trace commitments to detect silent model substitution in hosted Large Language Models, successfully rejecting various sophisticated attackers where previous methods failed.

Symbolon: Symbolic Execution by Learning Code Transformation

The paper presents Symbolon, a framework that learns and applies context-sensitively diverse code transformations to improve symbolic execution, increasing coverage and reducing costs.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.PLcs.SEEmpiricalRecentJun 27, 2026

Symbolon: Symbolic Execution by Learning Code Transformation

Jie Zhu, Penghui Li, Zhongxuan Li, Chihao Shen +3 more

The paper presents Symbolon, a framework that learns and applies context-sensitively diverse code transformations to improve symbolic execution, increasing coverage and reducing costs.

View →
cs.CRcs.AIRecent
Apr 20, 2026

Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs

Ziyang Liu

The paper proposes a commit-open protocol using SAE feature-trace commitments to detect silent model substitution in hosted Large Language Models, successfully rejecting various sophisticated attacker…

View →