Metraipolis › archive › dc_2af0bd784a9a
Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection — arXiv:2608.08100
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08100
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:58:13.491Z
- SHA-256 of the archived text
c78c4d354581f7d4d17bbc2be7a5b01ead3580b458398c2dc20581737118b13b- Stable URL of this page
https://metraipolis.com/documento/dc_2af0bd784a9a
How to cite
Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection — arXiv:2608.08100 — arXiv (en), https://arxiv.org/abs/2608.08100 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2af0bd784a9a (Metraipolis archive dc_2af0bd784a9a, sha256 c78c4d354581f7d4d17bbc2be7a5b01ead3580b458398c2dc20581737118b13b)
BibTeX
@misc{dc2af0bd784a9a,
title = {Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection — arXiv:2608.08100},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08100},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2af0bd784a9a; sha256 c78c4d354581f7d4d17bbc2be7a5b01ead3580b458398c2dc20581737118b13b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08100. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.08100 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:54:24.935Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).