paperAugust 2026Unreviewed

Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection

Kaysarul Anas Apurba, Md. Hasibul Hasan, Mahedee Zaman Moon, Sk. Md. Mizanur Rahman, Atsuo Inomata

Abstract

Retrieval-Augmented Generation (RAG) enables large language models to classify network flows and generate human-readable incident reports by retrieving semantically similar historical traffic from a vector knowledge base. However, the retrieval layer introduces vulnerabilities to knowledge poisoning and prompt-injection attacks. We present RAG-IDS, a three-tier multi-agent intrusion detection framework with a retrieval-boundary defense combining soft trust scoring, label-embedding consistency ch

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection
LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data
AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@misc{apurba2026defending,
  title = {{Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection}},
  author = {Kaysarul Anas Apurba and Md. Hasibul Hasan and Mahedee Zaman Moon and Sk. Md. Mizanur Rahman and Atsuo Inomata},
  year = {2026},
  month = aug,
  eprint = {2608.08100},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.08100}
}