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

Zhen Tan

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

Crypto×4AI×4NLP×3ML×3Vision×1

Frequent co-authors

Mohan Zhang2×
Yuqi Jia2×
Steven Jiang2×
Neil Zhenqiang Gong2×
Tianlong Chen2×
Dawn Song2×

Research Timeline

2026
Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance

This paper identifies and characterizes 'guidance injection,' a stealthy attack vector that embeds adversarial operational narratives into autonomous coding agents' bootstrap guidance, demonstrating high success rates and evasion capabilities.

To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model

The paper proposes MMGuard, a proactive defense mechanism that injects unlearnable, human-imperceptible perturbations into multimodal data to prevent unauthorized fine-tuning of Large Vision-Language Models (LVLMs).

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

This study provides the first large-scale measurement of prompt injection attacks in real-world LLM-based resume screening, finding that approximately 1% of resumes contain hidden injections.

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

This study provides the first systematic measurement of prompt injection attacks in a real-world LLM-based resume screening application, finding that approximately 1% of resumes contain hidden injections.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.CLRecentMay 27, 2026

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

Mohan Zhang, Yuqi Jia, Zhen Tan, Steven Jiang +3 more

This study provides the first large-scale measurement of prompt injection attacks in real-world LLM-based resume screening, finding that approximately 1% of resumes contain hidden injections.

View →
cs.CRcs.AIcs.CLRecentMay 27, 2026

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

Mohan Zhang, Yuqi Jia, Zhen Tan, Steven Jiang +3 more

This study provides the first systematic measurement of prompt injection attacks in a real-world LLM-based resume screening application, finding that approximately 1% of resumes contain hidden injecti…

View →
cs.CRcs.AIcs.CLRecentMay 14, 2026

To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model

Chengshuai Zhao, Zhen Tan, Dawei Li, Zhiyuan Yu +1 more

The paper proposes MMGuard, a proactive defense mechanism that injects unlearnable, human-imperceptible perturbations into multimodal data to prevent unauthorized fine-tuning of Large Vision-Language…

View →
cs.CRcs.AIRecentMar 20, 2026

Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance

Fazhong Liu, Zhuoyan Chen, Tu Lan, Haozhen Tan +5 more

This paper identifies and characterizes 'guidance injection,' a stealthy attack vector that embeds adversarial operational narratives into autonomous coding agents' bootstrap guidance, demonstrating h…

View →