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

Yuxiao Lu

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2AI×2NLP×2

Frequent co-authors

Ruoqi Guo2×
Yi Liu2×
Gelei Deng2×
Yiheng Xiong2×
Yuekang Li2×
Ying Zhang2×

Research Timeline

2026
MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content

The paper introduces MIRAGE, a novel pipeline that generates context-aware prompt injection attacks by injecting malicious text into user-generated content regions of mobile screenshots, successfully demonstrating the vulnerability of current GUI agents.

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content

The paper introduces MIRAGE, a novel pipeline that generates context-aware prompt injection attacks by embedding malicious text into user-generated content regions of mobile screenshots, successfully demonstrating the vulnerability of current VLM-driven GUI agents.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.CLRecentMay 27, 2026

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content

Ruoqi Guo, Yi Liu, Gelei Deng, Yiheng Xiong +6 more

The paper introduces MIRAGE, a novel pipeline that generates context-aware prompt injection attacks by injecting malicious text into user-generated content regions of mobile screenshots, successfully…

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

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content

Ruoqi Guo, Yi Liu, Gelei Deng, Yiheng Xiong +6 more

The paper introduces MIRAGE, a novel pipeline that generates context-aware prompt injection attacks by embedding malicious text into user-generated content regions of mobile screenshots, successfully…

View →