Ricardo Britto
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper develops and evaluates supervised machine learning models to detect malicious tool descriptions within the Model Context Protocol (MCP), achieving high detection rates in both binary and multiclass classification tasks.
This paper proposes using intentionally vulnerable test applications to validate threat modeling results, demonstrating that an LLM-assisted tool (ThreMoLIA) achieves superior vulnerability coverage compared to established tools like MTMT.
Papers
Validating Threat Modeling Results with the Help of Vulnerable Test Applications
This paper proposes using intentionally vulnerable test applications to validate threat modeling results, demonstrating that an LLM-assisted tool (ThreMoLIA) achieves superior vulnerability coverage c…