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

Zhiyang Dai

1 indexed paper

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

Publications per year

1
26

Top categories

Crypto×1AI×1

Frequent co-authors

Yansong Gao1×
Boyu Kuang1×
Haodong Li1×
Qi Chang1×
Gaurav Varshney1×
Derek Abbott1×

Research Timeline

2026
Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning

This paper repurposes the statistical signals from data-poisoning backdoor attacks on contrastive learning (CL) models to create a multi-level, effective watermarking scheme for dataset intellectual property (IP) protection.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 3, 2026

Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning

Zhiyang Dai, Yansong Gao, Boyu Kuang, Haodong Li +4 more

This paper repurposes the statistical signals from data-poisoning backdoor attacks on contrastive learning (CL) models to create a multi-level, effective watermarking scheme for dataset intellectual p…

View →