paperSeptember 2026Unreviewed

TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning

Muhaimin Bin Munir, Akib Jawad Ononto, Nazia Shehnaz Joynab, Bhavani Thuraisingham, Latifur Khan

Abstract

Retrieval-Augmented Generation (RAG) grounds large language models in external corpora, but implicit trust in retrieved documents creates a critical attack surface: PoisonedRAG shows that a handful of crafted passages can dominate dense retrieval and steer generation toward attacker-chosen answers. We present the Tri-Layer Sieve, a middleware defense that sanitizes retrieved evidence through cross-embedding-space clustering with an independent judge model, structural filtering of trigger-payload

Framework mappings

OWASP Top 10 for LLM Applications

LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data

Suggested from the entry's categories.

Cite

@misc{munir2026tris,
  title = {{TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning}},
  author = {Muhaimin Bin Munir and Akib Jawad Ononto and Nazia Shehnaz Joynab and Bhavani Thuraisingham and Latifur Khan},
  year = {2026},
  month = sep,
  eprint = {2609.00470},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.00470}
}