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

Yihan Wang

2 indexed papers

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

Publications per year

2
26

Top categories

ML×2Crypto×2NLP×1AI×1

Frequent co-authors

Jack Sanderson1×
Xiaoqian Lu1×
Gautam Kamath1×
Yiwei Lu1×
N. Asokan1×

Research Timeline

2026
Extracting Training Data from Diffusion Language Models via Infilling

The paper introduces 'infilling extraction' to accurately model training data memorization in Diffusion Language Models (DLMs), finding that bidirectional masking significantly increases the extractability of verbatim training data compared to traditional prefix-only methods.

Sequential Data Poisoning in LLM Post-Training

The paper introduces the threat model of sequential data poisoning, demonstrating that multiple, collaborating attackers can exploit compound vulnerabilities in LLM post-training pipelines that are invisible when analyzing individual stages.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CRRecentJun 3, 2026

Sequential Data Poisoning in LLM Post-Training

Jack Sanderson, Yihan Wang, Xiaoqian Lu, Gautam Kamath +1 more

The paper introduces the threat model of sequential data poisoning, demonstrating that multiple, collaborating attackers can exploit compound vulnerabilities in LLM post-training pipelines that are in…

View →
cs.CLcs.AIcs.CRRecentMay 22, 2026

Extracting Training Data from Diffusion Language Models via Infilling

Yihan Wang, N. Asokan

The paper introduces 'infilling extraction' to accurately model training data memorization in Diffusion Language Models (DLMs), finding that bidirectional masking significantly increases the extractab…

View →