Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows | Paper Citation Record

Observation 2378bb77-cbef-49bc-bcec-e9818a8fc263 · outbound

This paper cites Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:17.476603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63962b07-74e2-4e9d-b827-c35242452fe1 · outbound

This paper cites FLAG: Fraud detection with LLM-enhanced graph neural network.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows FLAG: Fraud detection with LLM-enhanced graph neural network

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:17.582243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df8422c3-852f-4496-ad3e-2d40102aa1d9 · outbound

This paper cites LLM-enhanced self-evolving reinforcement learning for multi-step e-commerce pay- ment fraud risk detection.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows LLM-enhanced self-evolving reinforcement learning for multi-step e-commerce pay- ment fraud risk detection

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:17.760024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c6077c-0cb0-43a4-ba4d-3d203bc62f9f · outbound

This paper cites Advanced Real-Time Fraud Detection Using RAG-Based LLMs.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Advanced Real-Time Fraud Detection Using RAG-Based LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:17.938720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd79c548-c47b-4860-b18a-a5493c27b52c · outbound

This paper cites LLM-assistedauthenticationandfrauddetection,.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows LLM-assistedauthenticationandfrauddetection,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:18.063127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7171ac90-634b-41f6-ae0b-ab4cbebbfe30 · outbound

This paper cites AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:18.415677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 562f4291-508b-4f6b-bdd2-96806c3837a2 · outbound

This paper cites SLM-Mod: Small Language Models Surpass LLMs at Content Moderation.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows SLM-Mod: Small Language Models Surpass LLMs at Content Moderation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:18.561141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2777191-b6e2-40aa-a1f6-ef7c773a282d · outbound

This paper cites CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:18.728116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 692958b1-aeb4-41f3-b15e-49334dd31303 · outbound

This paper cites EXPLICATE: Enhancing Phishing Detection through Explainable AI and LLM-Powered Interpretability.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows EXPLICATE: Enhancing Phishing Detection through Explainable AI and LLM-Powered Interpretability

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:18.864784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dac0124c-1020-4629-ae97-f426f0b615fa · outbound

This paper cites Co-investigator AI: The rise of agentic AI for smarter, trustworthy AML compliance narratives, 2025.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Co-investigator AI: The rise of agentic AI for smarter, trustworthy AML compliance narratives, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:18.994217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0808aa5f-557e-464c-90f2-40e3f6041d0a · outbound

This paper cites FAA Framework: A Large Language Model-Based Approach for Credit Card Fraud Investigations.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows FAA Framework: A Large Language Model-Based Approach for Credit Card Fraud Investigations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.069283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ecaf8ac-cb16-46f9-b9d3-1c1419778c20 · outbound

This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.120982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee90f312-5107-411e-a5a3-e2e13e65d86b · outbound

This paper cites PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.177718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 119e0060-e43c-4a9f-910d-c79a89ca5683 · outbound

This paper cites Selective Conformal Risk Control.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Selective Conformal Risk Control

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.248857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c77aa58-f4ba-4a7d-a9c2-9f84f1761d16 · outbound

This paper cites Enhancing the interpretability of SHAP values using LLMs, 2024.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Enhancing the interpretability of SHAP values using LLMs, 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.318217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9945c231-4833-45d2-801a-6200a58d1a14 · outbound

This paper cites Safeguarding Large Language Models: A Survey.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Safeguarding Large Language Models: A Survey

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.372134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca918491-74ac-4d57-8dff-e52206643b57 · outbound

This paper cites Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.432277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9eda4c6-3cf6-4826-bd79-31809754c8f7 · outbound

This paper cites A survey on large language model (LLM) security and privacy: The good, the bad, and the ugly,.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows A survey on large language model (LLM) security and privacy: The good, the bad, and the ugly,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.509653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1a0da57-ca2a-44db-9c48-ba7bfcd59edb · outbound

This paper cites Year-over-Year Developments in Financial Fraud Detection via Deep Learning: A Systematic Literature Review.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Year-over-Year Developments in Financial Fraud Detection via Deep Learning: A Systematic Literature Review

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.643424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74d2ec6a-8104-4ff0-b204-d393aa1da4b9 · outbound

This paper cites Large language models for financial fraud detection: A systematic review of methodologies, performance, and future directions.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Large language models for financial fraud detection: A systematic review of methodologies, performance, and future directions

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.723260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3700b3f8-b272-4154-946e-0e9a235d1b49 · outbound

This paper cites Applications of AI-based models for online fraud detection and analysis.Crime Science, 14(7), 2025.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Applications of AI-based models for online fraud detection and analysis.Crime Science, 14(7), 2025

Reference 21

Resolution: verified exact; doi, observed 2026-08-02T07:08:28.670495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b2426ecc-b60c-4424-afd8-6ac0aecb8abf · outbound

This paper cites Large language models in the abuse detection pipeline, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Large language models in the abuse detection pipeline, 2026

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.863146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7c6c49d-d04d-4a18-88c8-2cc5ad795f9b · outbound

This paper cites FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.932013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8488e9f-949f-4c99-8c80-3fe41c0255bc · outbound

This paper cites MeasuringwhatLLMsthinktheydo: SHAPfaithfulnessanddeployability on financial tabular classification, 2025.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows MeasuringwhatLLMsthinktheydo: SHAPfaithfulnessanddeployability on financial tabular classification, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.000754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62ac8f37-4f52-40ad-b1cc-44d7042493d1 · outbound

This paper cites Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.077337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f9dc42-46b5-4970-9d3c-59bc007c3153 · outbound

This paper cites Safety in Large Reasoning Models: A Survey.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Safety in Large Reasoning Models: A Survey

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.139263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebb48a25-053c-4371-b8c9-fc0236b50e85 · outbound

This paper cites DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.220512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e259eb8-1d3d-474c-878a-ab2eb6c5add3 · outbound

This paper cites Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.259839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f428ee8-e385-423a-82d5-0fe31cf31f66 · outbound

This paper cites Acomprehensivereviewof LLM-based content moderation: Advancements, challenges, and future directions, 2025.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Acomprehensivereviewof LLM-based content moderation: Advancements, challenges, and future directions, 2025

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.314032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15911858-b7cc-49d5-b079-a8313f68dcf2 · outbound

This paper cites Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey, 2025.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Security of LLM-based agents regarding attacks, defenses, and applications: A comprehensive survey, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.372316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c73b2d6-e0f9-4750-a524-991b4090d151 · outbound

This paper cites an unresolved cited work.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.404988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5f6afd8-5445-4f59-b359-e842317cb521 · outbound

This paper cites Content Moderation by LLM: From Accuracy to Legitimacy.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Content Moderation by LLM: From Accuracy to Legitimacy

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.486642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce04c4a3-6956-47e6-b5a2-8d341e12686f · outbound

This paper cites TELUSdigitaltrustandsafetytrends2025.https://www.telusdigital.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows TELUSdigitaltrustandsafetytrends2025.https://www.telusdigital

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.609474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65481bcf-9fc8-41cf-969c-eabe7213b6f8 · outbound

This paper cites LLMs for Explainable AI: A Comprehensive Survey.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows LLMs for Explainable AI: A Comprehensive Survey

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.676202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cced1deb-8dd4-491f-a597-f43af6c6d870 · outbound

This paper cites Dziemian, M.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Dziemian, M

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.759370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cd0834a-5a30-4754-a148-2575fad8eb37 · outbound

This paper cites FRAUDLLM: Zero-shot fraud detection with large language models, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows FRAUDLLM: Zero-shot fraud detection with large language models, 2026

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.828834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0285e250-e781-41ab-8a06-fadab6ed034c · outbound

This paper cites Reinforcement learning of large language models for interpretable credit card fraud detection, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Reinforcement learning of large language models for interpretable credit card fraud detection, 2026

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:20.932411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 719b3d5d-ea38-4fd2-8615-a9561b64e344 · outbound

This paper cites Telecom fraud detection based on large language models: A multi-role, multi-layer prompting strategy, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Telecom fraud detection based on large language models: A multi-role, multi-layer prompting strategy, 2026

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.031188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6a45dc9-c2f5-474a-a61d-bdd97df6e08e · outbound

This paper cites Telecom fraud recognition based on large language model neuron selection, 2025.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Telecom fraud recognition based on large language model neuron selection, 2025

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.117359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8f27073-efe6-4fe8-a813-ae8bdf5489f7 · outbound

This paper cites Can LLMs find fraudsters? multi-level LLM enhanced graph fraud detection, 2025.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Can LLMs find fraudsters? multi-level LLM enhanced graph fraud detection, 2025

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.200183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd318301-4d26-4762-8215-0ac23ae52cc7 · outbound

This paper cites Exploring the In-Context Learning Capabilities of LLMs for Money Laundering Detection in Financial Graphs.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Exploring the In-Context Learning Capabilities of LLMs for Money Laundering Detection in Financial Graphs

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.268179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1b77bc9-cce5-4688-9658-c58c32788714 · outbound

This paper cites an unresolved cited work.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.337198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4184226-9f46-42e2-a361-0d1698e8ea6a · outbound

This paper cites Large language models reproduce racial stereotypes when used for text annotation, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Large language models reproduce racial stereotypes when used for text annotation, 2026

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.419855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ddeeb3c-5413-4247-8315-ab354a459f29 · outbound

This paper cites Dialect vs demographics: Quantifying LLM bias from im- plicit linguistic signals vs.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Dialect vs demographics: Quantifying LLM bias from im- plicit linguistic signals vs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.512585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fc977fb-7f67-41b8-8df6-c99baac87642 · outbound

This paper cites When to invoke: Refining LLM fairness with toxicity assessment, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows When to invoke: Refining LLM fairness with toxicity assessment, 2026

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.582965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 913dd807-425e-44dd-99d1-4ef6f137f119 · outbound

This paper cites Longitudinalmonitoring of LLM content moderation of social issues, 2025.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Longitudinalmonitoring of LLM content moderation of social issues, 2025

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.647721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c5899e9-3d0e-49b5-8164-cab5570410f0 · outbound

This paper cites Prompt injection at- tacks in large language models and AI agent systems: A comprehensive review of vul- nerabilities, attack vectors, and defense mechanisms, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Prompt injection at- tacks in large language models and AI agent systems: A comprehensive review of vul- nerabilities, attack vectors, and defense mechanisms, 2026

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.762707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a89ced59-3bf8-41dc-91d3-39ecb95b73ae · outbound

This paper cites Semantic chameleon: Corpus-dependent poisoning attacks and defenses in RAG systems, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Semantic chameleon: Corpus-dependent poisoning attacks and defenses in RAG systems, 2026

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.824395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 973fae18-0444-4723-bcae-447da30b5ff7 · outbound

This paper cites DataexfiltrationfromSlackAIviaindirectpromptinjection.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows DataexfiltrationfromSlackAIviaindirectpromptinjection

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.906580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d332f9d-3f96-43e1-9061-42fa42a8bbc2 · outbound

This paper cites ServiceNow Now Assist AI agent vulnerability (BodySnatcher, cve-2025-12420),.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows ServiceNow Now Assist AI agent vulnerability (BodySnatcher, cve-2025-12420),

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:21.991812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbc2ec67-3aee-4b1c-b2b1-6eeb1ad41084 · outbound

This paper cites Detecting and analyzing prompt abuse in AI tools.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Detecting and analyzing prompt abuse in AI tools

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:22.137016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e8c56e-03f7-497b-a333-1c45800c7ea6 · outbound

This paper cites OWASP GenAI exploit round-up report q1 2026.https: //genai.owasp.org/2026/04/14/owasp-genai-exploit-round-up-report-q1-2026/,.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows OWASP GenAI exploit round-up report q1 2026.https: //genai.owasp.org/2026/04/14/owasp-genai-exploit-round-up-report-q1-2026/,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:22.211817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26974836-ea47-4e5a-b170-dafca61f7799 · outbound

This paper cites an unresolved cited work.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:22.469183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9510f26-2698-4c69-a7ef-a294baf6610f · outbound

This paper cites Breaking the chain: A causal analysis of LLM faithfulness to intermediate struc- tures, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Breaking the chain: A causal analysis of LLM faithfulness to intermediate struc- tures, 2026

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:22.672309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af2e034e-aa42-4961-bb91-0115015c0a4b · outbound

This paper cites Multi-layered framework for LLM hallucination mitigation in high-stakes applications: A tutorial, 2025.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Multi-layered framework for LLM hallucination mitigation in high-stakes applications: A tutorial, 2025

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:22.811347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbf5cdef-a274-4ffd-8414-7bcbdfa6acaf · outbound

This paper cites an unresolved cited work.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:22.317656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a089d754-05d9-4b06-be52-081688b0e346 · outbound

This paper cites Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.116966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c594956-b7ad-415e-bb25-583fb74fd094 · outbound

This paper cites Can large language models automate phishing warning explanations? a controlled experiment on effectiveness and user perception, 2025.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Can large language models automate phishing warning explanations? a controlled experiment on effectiveness and user perception, 2025

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.187092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71ec504e-d121-4036-a127-f028d0264c18 · outbound

This paper cites an unresolved cited work.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Unresolved cited work

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.268238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d42a87e4-4fdd-48a4-b1dc-927df1384132 · outbound

This paper cites Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:22.993466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06987d35-ad35-477b-abef-5fe29278b232 · outbound

This paper cites an unresolved cited work.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Unresolved cited work

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.361289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48b12ee2-ffc5-4171-bfc3-37178c625609 · outbound

This paper cites Domain Knowledge-Enhanced LLMs for Fraud and Concept Drift Detection.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Domain Knowledge-Enhanced LLMs for Fraud and Concept Drift Detection

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.445924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afe47d99-b6ea-4d9c-9bf1-4de9fbdd4bd6 · outbound

This paper cites LLM performance predictors: Learning when to escalate in hybrid human-AI moderation systems, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows LLM performance predictors: Learning when to escalate in hybrid human-AI moderation systems, 2026

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.512024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e19b6f40-5b9c-4ded-bbc0-0269db94434f · outbound

This paper cites an unresolved cited work.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Unresolved cited work

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.322568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01608456-5d0a-46ac-b486-83e630f2588f · outbound

This paper cites UCCI: Calibrated uncertainty for cost-optimal LLM cascade routing, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows UCCI: Calibrated uncertainty for cost-optimal LLM cascade routing, 2026

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.669203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2931a3bf-d6d4-4ec2-9941-87eb04599ab3 · outbound

This paper cites Compliance-scored best-of-N guardrail or- chestration for multimodal document generation in payments dispute defense, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Compliance-scored best-of-N guardrail or- chestration for multimodal document generation in payments dispute defense, 2026

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.755495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f4c2c1-12f1-446a-8119-9ddc50266a1e · outbound

This paper cites Robust and efficient guardrails with latent reasoning, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Robust and efficient guardrails with latent reasoning, 2026

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.813683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a68ae49-12bd-49af-bc0e-3d70b3d995ad · outbound

This paper cites Redefining AI red teaming in the agentic era: From weeks to hours, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Redefining AI red teaming in the agentic era: From weeks to hours, 2026

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.598570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 904009e3-d20f-4597-b98b-e3b9edf43940 · outbound

This paper cites AI agents may always fall for prompt injections,.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows AI agents may always fall for prompt injections,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.993917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e82dff18-7ea6-4f72-b25f-aa666543e3d5 · outbound

This paper cites SAGE: An LLM- driven self reflective agentic framework for fraud detection, 2026.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows SAGE: An LLM- driven self reflective agentic framework for fraud detection, 2026

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:23.908774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d14cceb2-66e2-4b8b-bea1-4f79f750fde6 · outbound

This paper cites an unresolved cited work.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Unresolved cited work

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:24.001849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75363083-5c36-481d-903b-e2745f9bb9fd · outbound

This paper cites A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.581859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aecad44-4622-4970-958c-c2e30e62020c · outbound

This paper cites an unresolved cited work.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Unresolved cited work

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:22.059647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c1ae580-f064-4936-a0fd-593d47fec544 · outbound

This paper cites LLM-Assisted Authentication and Fraud Detection.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows LLM-Assisted Authentication and Fraud Detection

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:18.241831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers