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

Tian Dong

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2AI×1

Frequent co-authors

Yanjun Chen1×
Shoufeng Zhang1×
Huaien Zhang1×
Yunlong Lyu1×
Keke Lian1×
Dong Zhang1×

Research Timeline

2026
AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents

The paper introduces AgentRAE, a novel backdoor attack that successfully forces mobile GUI agents to execute remote actions using visually natural triggers found in system notifications, achieving high success rates while remaining difficult to detect.

Hunting Vulnerability Variants in AI Infra: Measurement and Reference-Driven Detection

This paper measures the prevalence of recurring vulnerability patterns (variants) across multiple AI infrastructure repositories and proposes INFRASCOPE, a framework to automatically detect these variants.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentMay 19, 2026

Hunting Vulnerability Variants in AI Infra: Measurement and Reference-Driven Detection

Tian Dong, Yanjun Chen, Shoufeng Zhang, Huaien Zhang +5 more

This paper measures the prevalence of recurring vulnerability patterns (variants) across multiple AI infrastructure repositories and proposes INFRASCOPE, a framework to automatically detect these vari…

View →
cs.CRcs.AIRecentMar 24, 2026

AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents

Yutao Luo, Haotian Zhu, Shuchao Pang, Zhigang Lu +3 more

The paper introduces AgentRAE, a novel backdoor attack that successfully forces mobile GUI agents to execute remote actions using visually natural triggers found in system notifications, achieving hig…

View →