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

Pratibha Revankar

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

Kargi Chauhan1×

Research Timeline

2026
Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents

This paper proposes a multi-layered defense strategy combining pre-output monitoring, calibrated canary detection, and cumulative information-flow tracking to prevent LLM agents from exfiltrating sensitive credentials.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentJun 2, 2026

Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents

Kargi Chauhan, Pratibha Revankar

This paper proposes a multi-layered defense strategy combining pre-output monitoring, calibrated canary detection, and cumulative information-flow tracking to prevent LLM agents from exfiltrating sens…

View →