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

Dileepa Lakshan

1 indexed paper

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

Publications per year

1
26

Top categories

Crypto×1AI×1

Frequent co-authors

Udari Madhushani Sehwag1×
Zhengyang Shan1×
Heming Liu1×
Joseph Brandifino1×
Max Fenkell1×

Research Timeline

2026
ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents

The paper introduces ASPI, a benchmark showing that requiring LLM agents to seek clarification significantly amplifies their vulnerability to prompt injection attacks.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 17, 2026

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents

Udari Madhushani Sehwag, Zhengyang Shan, Heming Liu, Dileepa Lakshan +2 more

The paper introduces ASPI, a benchmark showing that requiring LLM agents to seek clarification significantly amplifies their vulnerability to prompt injection attacks.

View →