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

Shen Dong

1 indexed paper

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

Publications per year

1
26

Top categories

NLP×1AI×1Crypto×1

Frequent co-authors

Tiankai Yang1×
Jiate Li1×
Yi Nian1×
Ruiyao Xu1×
Ryan Rossi1×
Kaize Ding1×

Research Timeline

2026
No Attacker Needed: Unintentional Cross-User Contamination in Shared-State LLM Agents

This paper identifies and analyzes unintentional cross-user contamination (UCC), a failure mode where benign, scope-bound artifacts degrade the outcomes of different users in shared-state LLM agents, requiring artifact-level defenses.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIcs.CRRecentApr 1, 2026

No Attacker Needed: Unintentional Cross-User Contamination in Shared-State LLM Agents

Tiankai Yang, Jiate Li, Yi Nian, Shen Dong +4 more

This paper identifies and analyzes unintentional cross-user contamination (UCC), a failure mode where benign, scope-bound artifacts degrade the outcomes of different users in shared-state LLM agents,…

View →