Is PromptGuard superseded?

PromptGuard (Retrieval-augmented generation): superseded — cited as a baseline and beaten by newer methods. 1 paper(s) critique it, 1 beat it on benchmarks — #153 of 1179 most-superseded. Sub-problem: cluster led by RobustRAG. Newer alternatives in the same sub-problem include CORDON-MAS, BiRD, CleanBase, Beyond Factual Grounding, RAGShield.

Method Drift›Retrieval-augmented generation

Superseded baseline#153 of 1,179 most-superseded

PromptGuard

Retrieval-augmented generation

superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 1 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites PromptGuard as a baseline.

“While general prompt injection detection methods~promptguard2024,liu2025datasentinel can be applied to identify malicious documents, our experiments show that their effectiveness is limited.”
— CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

Beaten on benchmarks

Head-to-head results where a newer method reports beating PromptGuard. Values are copied from the source paper's tables — verify against the cited paper.

CleanBase beats PromptGuard · FPR [NQ dataset, Naive Attack]
1.8 vs 35.9
CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.