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

Junhao Li

3 indexed papers

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

Publications per year

3
26

Top categories

Crypto×3AI×1

Frequent co-authors

Zhenhao Xu1×
Wenhan Chang1×
Yichuan Chen1×
Yuxin Fang1×
Junhao Liu1×
Tianqing Zhu1×

Research Timeline

2026
Functional Subspace Watermarking for Large Language Models

The paper proposes Functional Subspace Watermarking (FSW), a robust method that embeds ownership signals into a stable, low-dimensional functional subspace of LLMs, significantly improving detection accuracy against model modifications.

Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents

The paper introduces the PrivacyIceberg framework to systematically categorize and empirically demonstrate the high risk of automated, deep personal profiling using LLM agents, revealing a significant gap between public concern and platform safeguards.

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis

The paper proposes Safety Context Injection (SCI), an inference-time framework that prepends a structured external risk report to protect Large Reasoning Models (LRMs) against sophisticated jailbreaks, significantly reducing attack success rates.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentMay 12, 2026

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis

Zhenhao Xu, Wenhan Chang, Yichuan Chen, Yuxin Fang +2 more

The paper proposes Safety Context Injection (SCI), an inference-time framework that prepends a structured external risk report to protect Large Reasoning Models (LRMs) against sophisticated jailbreaks…

View →
cs.CRRecentMay 7, 2026

Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents

Jiahao Chen, Qi Zhang, Ruixiao Lin, Chunyi Zhou +6 more

The paper introduces the PrivacyIceberg framework to systematically categorize and empirically demonstrate the high risk of automated, deep personal profiling using LLM agents, revealing a significant…

View →
cs.CRcs.AIRecentMar 19, 2026

Functional Subspace Watermarking for Large Language Models

Zikang Ding, Junhao Li, Suling Wu, Junchi Yao +2 more

The paper proposes Functional Subspace Watermarking (FSW), a robust method that embeds ownership signals into a stable, low-dimensional functional subspace of LLMs, significantly improving detection a…

View →