A Privacy-Preserving Middleware Architecture for Detecting Prompt Injection and Sensitive Data Exposure in Large-Language-Model Interactions

Abstract

The deployment of large language models (LLMs) in real-world applications introduces a compounding security problem: detecting adversarial inputs such as prompt injection and jailbreak-driven data leakage while simultaneously preventing the detection mechanism itself from becoming a source of data exposure. Existing approaches address either detection effectiveness or privacy preservation, but rarely both in a unified, deployable architecture. This paper proposes and evaluates a privacy-preservi

Categories

Framework mappings

Suggested from the entry's categories.

@article{hsine2026privacypreserving,
  title = {{A Privacy-Preserving Middleware Architecture for Detecting Prompt Injection and Sensitive Data Exposure in Large-Language-Model Interactions}},
  author = {Adam Ait Hsine and A. Arabo},
  year = {2026},
  month = aug,
  journal = {Electronics},
  doi = {10.3390/electronics15163554},
  url = {https://www.semanticscholar.org/paper/0946d10598a3836423ad37115c73c58a45a9874d}
}