Enhancing System Security: LLM-Driven Defense Against Prompt Injection Vulnerabilities

Abstract

This article examines cybersecurity vulnerabilities in systems utilizing Language Model Interfaces, focusing on the challenges of building secure systems. It provides an overview of current interfaces and their associated risks. A key contribution is the design of a prompt analysis and injection detection subsystem, which assesses input relevance and security. The integration of an additional Filter level in the system safeguards against prompt injection attacks by pre-processing user requests a

Categories

Framework mappings

Suggested from the entry's categories.

@inproceedings{muliarevych2024enhancing,
  title = {{Enhancing System Security: LLM-Driven Defense Against Prompt Injection Vulnerabilities}},
  author = {Oleksandr Muliarevych},
  year = {2024},
  month = oct,
  booktitle = {International Conference on Modern Problems of Radio Engineering, Telecommunications and Computer Science},
  doi = {10.1109/TCSET64720.2024.10755823},
  url = {https://www.semanticscholar.org/paper/95be2ab522131b725b79062db7ceb849c924562e}
}