RAG-IDS protects a retrieval-augmented intrusion detection pipeline with a label-embedding consistency check, but the protected system only beats the unprotected one at 1% poisoning and underperforms it at 10% and above.
UNSW-NB15: A Comprehensive Data Set for Network Intrusion Detection Systems,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection
RAG-IDS protects a retrieval-augmented intrusion detection pipeline with a label-embedding consistency check, but the protected system only beats the unprotected one at 1% poisoning and underperforms it at 10% and above.