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

Tianyu Zhang

2 indexed papers

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

Publications per year

2
26

Top categories

AI×2NLP×1Crypto×1

Frequent co-authors

Yuanhe Zhao1×
Huafei Xing1×
Derek F. Wong1×
Jianbin Li1×
Tao Fang1×
Kun Wang1×

Research Timeline

2026
ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

The paper introduces ProjLens, an interpretability framework that reveals that backdoor vulnerabilities in Multimodal Large Language Models (MLLMs) are encoded within a low-rank subspace of the projector, causing a measurable semantic shift in poisoned inputs.

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

A multi-agent framework is proposed to sanitize retrieved content in Retrieval-Augmented Generation while preserving semantic core and reducing privacy leakage.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIEmpiricalRecentJun 23, 2026

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

Yuanhe Zhao, Tianyu Zhang, Huafei Xing, Derek F. Wong +2 more

A multi-agent framework is proposed to sanitize retrieved content in Retrieval-Augmented Generation while preserving semantic core and reducing privacy leakage.

View →
cs.CRcs.AIApr 21, 2026

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

Kun Wang, Cheng Qian, Miao Yu, Lilan Peng +5 more

The paper introduces ProjLens, an interpretability framework that reveals that backdoor vulnerabilities in Multimodal Large Language Models (MLLMs) are encoded within a low-rank subspace of the projec…

View →