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

Mingxun Zhou

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×3AI×3NLP×1

Frequent co-authors

Yijia Fang2×
Yiqing Feng2×
Bingyu Li2×
Jiahao Huo1×
Wenjie Qu1×
Yibo Yan1×

Research Timeline

2026
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

SAMark introduces a self-anchored text watermarking framework that achieves high robustness (up to 90.2% TP@FP1%) against challenging paragraph-level paraphrasing attacks by establishing a step-independent green region in semantic space.

KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing

The paper introduces KBF, a novel black-box auditing protocol that fingerprints LLM APIs by analyzing stable numerical recall near the knowledge boundary, effectively detecting model substitutions and inconsistencies in third-party API endpoints.

KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing

The paper introduces KBF, a low-cost black-box auditing protocol that fingerprints LLM APIs by analyzing stable numerical recall near the knowledge boundary, successfully detecting numerous model substitutions and inconsistencies across various production endpoints.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 28, 2026

KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing

Yijia Fang, Yiqing Feng, Bingyu Li, Mingxun Zhou

The paper introduces KBF, a novel black-box auditing protocol that fingerprints LLM APIs by analyzing stable numerical recall near the knowledge boundary, effectively detecting model substitutions and…

View →
cs.CRcs.AIRecentMay 28, 2026

KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing

Yijia Fang, Yiqing Feng, Bingyu Li, Mingxun Zhou

The paper introduces KBF, a low-cost black-box auditing protocol that fingerprints LLM APIs by analyzing stable numerical recall near the knowledge boundary, successfully detecting numerous model subs…

View →
cs.CRcs.AIcs.CLRecentMay 25, 2026

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

Jiahao Huo, Wenjie Qu, Yibo Yan, Kening Zheng +4 more

SAMark introduces a self-anchored text watermarking framework that achieves high robustness (up to 90.2% TP@FP1%) against challenging paragraph-level paraphrasing attacks by establishing a step-indepe…

View →