@prefix this: <
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo
> .
@prefix sub: <
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/
> .
@prefix np: <
http://www.nanopub.org/nschema#
> .
@prefix dct: <
http://purl.org/dc/terms/
> .
@prefix xsd: <
http://www.w3.org/2001/XMLSchema#
> .
@prefix rdfs: <
http://www.w3.org/2000/01/rdf-schema#
> .
@prefix prov: <
http://www.w3.org/ns/prov#
> .
@prefix npx: <
http://purl.org/nanopub/x/
> .
sub:Head
{
this:
np:hasAssertion
sub:assertion
;
np:hasProvenance
sub:provenance
;
np:hasPublicationInfo
sub:pubinfo
;
a
np:Nanopublication
.
}
sub:assertion
{
<
https://doi.org/10.48550/arXiv.2601.22485
>
dct:title
"FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks" ;
<
http://purl.org/spar/cito/describes
> <
https://neverblink.eu/ontologies/llm-kg/methods#FraudShield
> ;
<
http://purl.org/spar/cito/discusses
> <
https://neverblink.eu/ontologies/llm-kg/methods#GoalPrioritization
> , <
https://neverblink.eu/ontologies/llm-kg/methods#SafetyPrompt
> , <
https://neverblink.eu/ontologies/llm-kg/methods#SelfReminder
> ;
a
prov:Entity
.
<
https://neverblink.eu/ontologies/llm-kg/methods#FraudShield
>
dct:subject
<
https://neverblink.eu/ontologies/llm-kg/categories#SynergizedReasoning
> ;
a
<
http://purl.org/spar/fabio/Workflow
> ;
rdfs:comment
"FraudShield is a novel framework that leverages LLMs to dynamically construct and refine a fraud tactic-keyword knowledge graph. This KG is then used to augment LLM inputs with structured evidence (XML-tagged keywords and rationales) during inference, thereby enhancing the LLM's reasoning capabilities for robust fraud detection. This integrated approach, where LLMs contribute to KG creation and the KG in turn guides LLM reasoning, exemplifies a synergistic interaction focused on mutual enhancement for improved reasoning." ;
rdfs:label
"FraudShield" ;
<
https://neverblink.eu/ontologies/llm-kg/hasTopCategory
> <
https://neverblink.eu/ontologies/llm-kg/top-categories#SynergizedLLMKG
> .
<
https://neverblink.eu/ontologies/llm-kg/methods#GoalPrioritization
>
a
<
http://purl.org/spar/fabio/Workflow
> ;
rdfs:label
"Goal Prioritization" .
<
https://neverblink.eu/ontologies/llm-kg/methods#SafetyPrompt
>
a
<
http://purl.org/spar/fabio/Workflow
> ;
rdfs:label
"Safety Prompt" .
<
https://neverblink.eu/ontologies/llm-kg/methods#SelfReminder
>
a
<
http://purl.org/spar/fabio/Workflow
> ;
rdfs:label
"Self-Reminder" .
}
sub:provenance
{
sub:assertion
prov:wasAttributedTo
<
https://neverblink.eu/ontologies/llm-kg/agent
> ;
prov:wasDerivedFrom
<
https://doi.org/10.48550/arXiv.2601.22485
> .
}
sub:pubinfo
{
this:
dct:created
"2026-02-26T15:54:42.214Z"^^
xsd:dateTime
;
dct:creator
<
https://neverblink.eu/ontologies/llm-kg/agent
> ;
npx:hasNanopubType
<
https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult
> ;
rdfs:label
"LLM-KG assessment for paper 10.48550/arXiv.2601.22485" .
sub:sig
npx:hasAlgorithm
"RSA" ;
npx:hasPublicKey
"MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB" ;
npx:hasSignature
"BP9lFDtWQLs2Hx3c4x1d3LEtfw04DVKba26/TpqqTc/cWg54qWyhDkEYAaHRzdDu93ST2cXa7KkebY1wWvLZFXNC/ceSfAhJw4K0QxE7K6dk1REI7akmsz3eNzCwvT/V2w0z6J1PX0TGbsILYIabn4RXvxuxI0x7HNIfsI2ToCkzm3Rs1C2RWgg/ExnyIZE0T2PclSpF8dxAgFlyk//dqTGwM48jPfEgWKLU0a34kCls0e0tbGW1LVmSMepgApjbWJ7eciX9/MWiXZtj6NjY/NjNgHw3oDVosXxiJcbU6eBNNjNA5oD2VToMLEmGGDh751+OdFeL6aSkt7ouJeC8gA==" ;
npx:hasSignatureTarget
this:
;
npx:signedBy
<
https://neverblink.eu/ontologies/llm-kg/agent
> .
}