https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/Head
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo
http://www.nanopub.org/nschema#hasAssertion
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/assertion
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo
http://www.nanopub.org/nschema#hasProvenance
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/provenance
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo
http://www.nanopub.org/nschema#hasPublicationInfo
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/pubinfo
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo
http://www.w3.org/1999/02/22-rdf-syntax-ns#type
http://www.nanopub.org/nschema#Nanopublication
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/assertion
https://doi.org/10.48550/arXiv.2601.22485
http://purl.org/dc/terms/title
FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
https://doi.org/10.48550/arXiv.2601.22485
http://purl.org/spar/cito/describes
https://neverblink.eu/ontologies/llm-kg/methods#FraudShield
https://doi.org/10.48550/arXiv.2601.22485
http://purl.org/spar/cito/discusses
https://neverblink.eu/ontologies/llm-kg/methods#GoalPrioritization
https://doi.org/10.48550/arXiv.2601.22485
http://purl.org/spar/cito/discusses
https://neverblink.eu/ontologies/llm-kg/methods#SafetyPrompt
https://doi.org/10.48550/arXiv.2601.22485
http://purl.org/spar/cito/discusses
https://neverblink.eu/ontologies/llm-kg/methods#SelfReminder
https://doi.org/10.48550/arXiv.2601.22485
http://www.w3.org/1999/02/22-rdf-syntax-ns#type
http://www.w3.org/ns/prov#Entity
https://neverblink.eu/ontologies/llm-kg/methods#FraudShield
http://purl.org/dc/terms/subject
https://neverblink.eu/ontologies/llm-kg/categories#SynergizedReasoning
https://neverblink.eu/ontologies/llm-kg/methods#FraudShield
http://www.w3.org/1999/02/22-rdf-syntax-ns#type
http://purl.org/spar/fabio/Workflow
https://neverblink.eu/ontologies/llm-kg/methods#FraudShield
http://www.w3.org/2000/01/rdf-schema#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.
https://neverblink.eu/ontologies/llm-kg/methods#FraudShield
http://www.w3.org/2000/01/rdf-schema#label
FraudShield
https://neverblink.eu/ontologies/llm-kg/methods#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
http://www.w3.org/1999/02/22-rdf-syntax-ns#type
http://purl.org/spar/fabio/Workflow
https://neverblink.eu/ontologies/llm-kg/methods#GoalPrioritization
http://www.w3.org/2000/01/rdf-schema#label
Goal Prioritization
https://neverblink.eu/ontologies/llm-kg/methods#SafetyPrompt
http://www.w3.org/1999/02/22-rdf-syntax-ns#type
http://purl.org/spar/fabio/Workflow
https://neverblink.eu/ontologies/llm-kg/methods#SafetyPrompt
http://www.w3.org/2000/01/rdf-schema#label
Safety Prompt
https://neverblink.eu/ontologies/llm-kg/methods#SelfReminder
http://www.w3.org/1999/02/22-rdf-syntax-ns#type
http://purl.org/spar/fabio/Workflow
https://neverblink.eu/ontologies/llm-kg/methods#SelfReminder
http://www.w3.org/2000/01/rdf-schema#label
Self-Reminder
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/provenance
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/assertion
http://www.w3.org/ns/prov#wasAttributedTo
https://neverblink.eu/ontologies/llm-kg/agent
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/assertion
http://www.w3.org/ns/prov#wasDerivedFrom
https://doi.org/10.48550/arXiv.2601.22485
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/pubinfo
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo
http://purl.org/dc/terms/created
2026-02-26T15:54:42.214Z
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo
http://purl.org/dc/terms/creator
https://neverblink.eu/ontologies/llm-kg/agent
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo
http://purl.org/nanopub/x/hasNanopubType
https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo
http://www.w3.org/2000/01/rdf-schema#label
LLM-KG assessment for paper 10.48550/arXiv.2601.22485
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/sig
http://purl.org/nanopub/x/hasAlgorithm
RSA
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/sig
http://purl.org/nanopub/x/hasPublicKey
MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/sig
http://purl.org/nanopub/x/hasSignature
BP9lFDtWQLs2Hx3c4x1d3LEtfw04DVKba26/TpqqTc/cWg54qWyhDkEYAaHRzdDu93ST2cXa7KkebY1wWvLZFXNC/ceSfAhJw4K0QxE7K6dk1REI7akmsz3eNzCwvT/V2w0z6J1PX0TGbsILYIabn4RXvxuxI0x7HNIfsI2ToCkzm3Rs1C2RWgg/ExnyIZE0T2PclSpF8dxAgFlyk//dqTGwM48jPfEgWKLU0a34kCls0e0tbGW1LVmSMepgApjbWJ7eciX9/MWiXZtj6NjY/NjNgHw3oDVosXxiJcbU6eBNNjNA5oD2VToMLEmGGDh751+OdFeL6aSkt7ouJeC8gA==
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/sig
http://purl.org/nanopub/x/hasSignatureTarget
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo
https://w3id.org/np/RAktdmO7e56HyQlAV5G13k-17PnfVW-v6B-5FE6h3ZZwo/sig
http://purl.org/nanopub/x/signedBy
https://neverblink.eu/ontologies/llm-kg/agent