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

Song Li

2 indexed papers

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

Publications per year

2
26

Top categories

Stats Theory×1Info Theory×1Crypto×1

Frequent co-authors

Gao Huang1×
Pengyu Sun1×
Qishu Jin1×
Enhao Huang1×
Zifeng Kang1×
Xin Liu1×

Research Timeline

2026
VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers

VIPER-MCP is a novel, end-to-end automated framework that detects and dynamically confirms the exploitability of taint-style vulnerabilities in Model Context Protocol (MCP) servers, achieving high-fidelity vulnerability discovery in real-world systems.

Low-Rank Matrix Recovery via Heavy-Tailed Quadratic Sampling

This paper establishes recovery guarantees for low-rank Hermitian matrices from quadratic sampling matrices under the assumption of finite 4+δ moments of the entries.

Highlighted terms show continued research focus across papers

Papers

math.STcs.ITTheoreticalRecentJul 9, 2026

Low-Rank Matrix Recovery via Heavy-Tailed Quadratic Sampling

Gao Huang, Song Li

This paper establishes recovery guarantees for low-rank Hermitian matrices from quadratic sampling matrices under the assumption of finite 4+δ moments of the entries.

View →
cs.CRMay 20, 2026

VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers

Pengyu Sun, Qishu Jin, Enhao Huang, Zifeng Kang +3 more

VIPER-MCP is a novel, end-to-end automated framework that detects and dynamically confirms the exploitability of taint-style vulnerabilities in Model Context Protocol (MCP) servers, achieving high-fid…

View →