CASCADE: A Cascaded Hybrid Defense Architecture for Prompt Injection Detection in MCP-Based Systems

Abstract

Model Context Protocol (MCP) is a rapidly adopted standard for defining and invoking external tools in LLM applications. The multi-layered architecture of MCP introduces new attack surfaces such as tool poisoning, in addition to traditional prompt injection. Existing defense systems suffer from limitations including high false positive rates, API dependency, or white-box access requirements. In this study, we propose CASCADE, a three-tiered cascaded defense architecture for MCP-based systems: (i

Categories

Framework mappings

Suggested from the entry's categories.

@misc{turgut2026cascade,
  title = {{CASCADE: A Cascaded Hybrid Defense Architecture for Prompt Injection Detection in MCP-Based Systems}},
  author = {İpek Abasıkeleş Turgut and Edip Gümüş},
  year = {2026},
  month = apr,
  eprint = {2604.17125},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.17125}
}