LLM Firewall Using Validator Agent for Prevention Against Prompt Injection Attacks
Applied Sciences · 21.12.2025 · 16 (1) · 85
DOI: 10.3390/app16010085 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 21.12.2025. Verfasst von Michal Podpora und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union from the European Regional Development Fund.
Abstract (Originalsprache)
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 network firewalls, which monitor semantic boundaries, we position the Validator Agent as a response firewall performing multi-feature security checks: prompt injection detection, policy compliance verification, sensitive information redaction, and toxic content filtering. While existing defense approaches focus mainly on input-level screening, our architecture proposes to analyze the output, where a successful attack becomes more obvious. The proposed architecture was verified to be viable using the Polish Bielik 2.3 LLM in an on-premise RAG system designed for energy auditing.
Förderung
- European Union from the European Regional Development Fund
Zitieren
APA
Podpora, M., Baranowski, M., Chopcian, M., Kwasniewicz, L., & Radziewicz, W. (2025). LLM Firewall Using Validator Agent for Prevention Against Prompt Injection Attacks. Applied Sciences, 16(1), 85. https://doi.org/10.3390/app16010085
Vancouver
Podpora M, Baranowski M, Chopcian M, Kwasniewicz L, Radziewicz W. LLM Firewall Using Validator Agent for Prevention Against Prompt Injection Attacks. Applied Sciences. 2025;16(1):85. doi:10.3390/app16010085
BibTeX
@article{Podpora2025,
author = {Podpora, Michal and Baranowski, Marek and Chopcian, Maciej and Kwasniewicz, Lukasz and Radziewicz, Wojciech},
title = {LLM Firewall Using Validator Agent for Prevention Against Prompt Injection Attacks},
journal = {Applied Sciences},
year = {2025},
volume = {16},
number = {1},
pages = {85},
doi = {10.3390/app16010085}
}
EUVIMED