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

Yanzhou Mu

2 indexed papers

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

Publications per year

2
26

Top categories

Software Eng.×2ML×1Crypto×1

Frequent co-authors

Zhenyu Chen2×
Chunrong Fang2×
Jiatao Ge1×
Yinglong Zou1×
Yibo Hu1×
Yuan Xiao1×

Research Timeline

2026
Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets

FunPoison introduces a functionality-preserving poisoning technique that injects small, compilable weak-use fragments into code datasets to prevent unauthorized use of CodeLLMs without breaking the code's functionality.

Grounding Deep Learning Framework Testing in Data Flow

This paper introduces FlowMuT, a mutation-based testing method for deep learning frameworks that captures runtime tensor states and operator input requirements to identify bugs.

Highlighted terms show continued research focus across papers

Papers

cs.SEcs.LGEmpiricalRecentOct 11, 2026

Grounding Deep Learning Framework Testing in Data Flow

Jiatao Ge, Yanzhou Mu, Yinglong Zou, Yibo Hu +2 more

This paper introduces FlowMuT, a mutation-based testing method for deep learning frameworks that captures runtime tensor states and operator input requirements to identify bugs.

View →
cs.CRcs.SEApr 24, 2026

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets

Yuan Xiao, Jiaming Wang, Yuchen Chen, Wei Song +7 more

FunPoison introduces a functionality-preserving poisoning technique that injects small, compilable weak-use fragments into code datasets to prevent unauthorized use of CodeLLMs without breaking the co…

View →