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

NhatHai Phan

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2ML×1NLP×1

Frequent co-authors

Khang Tran1×
Yazan Boshmaf1×
Issa Khalil1×
Ting Yu1×
Md Rizwan Parvez1×
Kieu Dang1×

Research Timeline

2026
Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection

The paper proposes SAFESEAL, a novel key-conditioned watermarking framework that embeds robust, provider-specific watermarks into LLM outputs with minimal semantic distortion, effectively protecting intellectual property.

Poison with Style: A Practical Poisoning Attack on Code Large Language Models

The paper introduces Poison-with-Style (PwS), a stealthy model poisoning attack that exploits developers' inherent code styles as covert triggers to make Code LLMs generate vulnerable code without explicit prompts.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.LGRecentMay 26, 2026

Poison with Style: A Practical Poisoning Attack on Code Large Language Models

Khang Tran, Yazan Boshmaf, Issa Khalil, NhatHai Phan +2 more

The paper introduces Poison-with-Style (PwS), a stealthy model poisoning attack that exploits developers' inherent code styles as covert triggers to make Code LLMs generate vulnerable code without exp…

View →
cs.CRcs.CLRecentMay 22, 2026

Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection

Kieu Dang, Phung Lai, NhatHai Phan, Yelong Shen +1 more

The paper proposes SAFESEAL, a novel key-conditioned watermarking framework that embeds robust, provider-specific watermarks into LLM outputs with minimal semantic distortion, effectively protecting i…

View →