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

arXiv: https://arxiv.org/abs/2608.08100 · HTML: https://mlsanity.com/paper/2608.08100/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)
- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 20 of 20)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection](https://mlsanity.com/paper/1802.09089/) (2018)
- [A Survey of Network-based Intrusion Detection Data Sets](https://mlsanity.com/paper/1903.02460/) (2019)
- [Security Evaluation of Pattern Classifiers under Attack](https://mlsanity.com/paper/1709.00609/) (2017)
- [Practical Poisoning Attacks against Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.03957/) (2025)
- [SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model](https://mlsanity.com/paper/2501.18636/) (2025)
- [Traceback of Poisoning Attacks to Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.21668/) (2025)
- [FlowTransformer: A Transformer Framework for Flow-based Network Intrusion Detection Systems](https://mlsanity.com/paper/2304.14746/) (2023)
- [CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models](https://mlsanity.com/paper/2505.19864/) (2025)
- [CyberRAG: An Agentic RAG cyber attack classification and reporting tool](https://mlsanity.com/paper/2507.02424/) (2025)
- [Defending Against Knowledge Poisoning Attacks During Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.02835/) (2025)
- [MA-IDS: Multi-Agent RAG Framework for IoT Network Intrusion Detection with an Experience Library](https://mlsanity.com/paper/2604.05458/) (2026)

## Abstract (arXiv)

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 checking (LECC), and prompt sanitization, designed to recover classification quality under retrieval-layer attack. Experiments on CIC-UNSW-NB15 show recovery relative to clean undefended performance ranging from R=1.0 at 1% poisoning to R=0.57 at 30%, with negligible clean-performance overhead. Under prompt injection, multi-document retrieval limits label-flip success to 0.6-2.4%, compared with 35-55% for single-document retrieval. Ablation results show that LECC is the primary contributor to robustness, while soft trust-based demotion outperforms hard filtering. The defended RAG pipeline offers an explainable, attack-resilient foundation for intrusion detection, well suited for hybrid deployment alongside high-throughput classifiers.