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

Melissa Umble

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

Soumil Datta1×
Daniel S. Brown1×
Guanhong Tao1×

Research Timeline

2026
A Sentence Relation-Based Approach to Sanitizing Malicious Instructions

The paper introduces SONAR, a prompt sanitization framework that uses natural language inference metrics to identify and remove malicious instructions injected into LLM prompts, achieving near-zero attack success rates.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 1, 2026

A Sentence Relation-Based Approach to Sanitizing Malicious Instructions

Soumil Datta, Melissa Umble, Daniel S. Brown, Guanhong Tao

The paper introduces SONAR, a prompt sanitization framework that uses natural language inference metrics to identify and remove malicious instructions injected into LLM prompts, achieving near-zero at…

View →