DT-GenShield: A Digital Twin-Driven Runtime Security Architecture for Protecting Large Language Models Against Indirect Prompt Injection

Abstract

Large Language Models (LLMs) are increasingly deployed in security-critical applications but remain vulnerable to indirect prompt injection attacks that cannot be fully addressed by conventional prompt detection techniques. This paper proposes DT-GenShield, a Digital Twin-driven runtime security architecture that integrates semantic threat detection, operational state representation, policy-guided mediation, and runtime logging to protect LLM-based systems before model inference. The proposed ar

Categories

Framework mappings

Suggested from the entry's categories.

@article{alnemari2026dtgenshield,
  title = {{DT-GenShield: A Digital Twin-Driven Runtime Security Architecture for Protecting Large Language Models Against Indirect Prompt Injection}},
  author = {Alaa Alnemari and Mashael M. Alsulami},
  year = {2026},
  month = aug,
  journal = {Electronics},
  doi = {10.3390/electronics15163640},
  url = {https://www.semanticscholar.org/paper/689031f7b55edb5c81db55047a445d9f068415d1}
}