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

Ziyuan Yang

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2NLP×1

Frequent co-authors

Farhan Sheth1×
Yongying Lan1×
Si Yong Yeo1×
Yan Liang1×
Mengyu Sun1×
Joey Tianyi Zhou1×

Research Timeline

2026
From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation

The paper proposes SubPopMark, a novel subpopulation-driven framework that injects harmless, verifiable markers into distilled datasets to prevent copyright infringement and data leakage.

Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models

The paper introduces HERALD, a token-level cryptographic redaction framework that encrypts only sensitive tokens in clinical text, enabling privacy-preserving LLM deployment without significant loss of utility.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.CRRecentJun 2, 2026

Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models

Farhan Sheth, Ziyuan Yang, Yongying Lan, Si Yong Yeo

The paper introduces HERALD, a token-level cryptographic redaction framework that encrypts only sensitive tokens in clinical text, enabling privacy-preserving LLM deployment without significant loss o…

View →
cs.CRRecentMay 13, 2026

From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation

Yan Liang, Ziyuan Yang, Mengyu Sun, Joey Tianyi Zhou +1 more

The paper proposes SubPopMark, a novel subpopulation-driven framework that injects harmless, verifiable markers into distilled datasets to prevent copyright infringement and data leakage.

View →