LLM Firewall Using Validator Agent for Prevention Against Prompt Injection Attacks

Abstract

Large Language Models with Retrieval-Augmented Generation are considered to be modern, chat-native interfaces to enterprise knowledge. However, deploying such systems safely requires precautions more advanced than input filtering. Numerous LLM-related security threats (including the top one: prompt injection attacks) demand robust defense mechanisms beyond input filtering. This paper extends our dual-agent RAG architecture as an LLM firewall with output-level security validation. Similar to netw

Categories

Framework mappings

Suggested from the entry's categories.

@article{podpora2025llm,
  title = {{LLM Firewall Using Validator Agent for Prevention Against Prompt Injection Attacks}},
  author = {Michal Podpora and Marek Baranowski and Maciej Chopcian and Lukasz Kwasniewicz and Wojciech Radziewicz},
  year = {2025},
  month = dec,
  journal = {Applied Sciences},
  doi = {10.3390/app16010085},
  url = {https://doi.org/10.3390/app16010085}
}