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

Dongcheng Zhang

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Crypto×1AI×1NLP×1

Frequent co-authors

Yiqing Jiang1×

Research Timeline

2026
Owner-Harm: A Missing Threat Model for AI Agent Safety

The paper introduces Owner-Harm, a formal threat model addressing the critical blind spot of AI agents harming their own deployers, demonstrating that specialized defenses are needed beyond generic safety measures.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.CLRecentApr 20, 2026

Owner-Harm: A Missing Threat Model for AI Agent Safety

Dongcheng Zhang, Yiqing Jiang

The paper introduces Owner-Harm, a formal threat model addressing the critical blind spot of AI agents harming their own deployers, demonstrating that specialized defenses are needed beyond generic sa…

View →