Advanced Real-Time Fraud Detection Using RAG-Based LLMs

2025-01-25

AI Summary

To address the escalating threats of telephone fraud and identity spoofing, this paper proposes an end-to-end real-time anti-fraud system. Methodologically, it integrates ASR-based real-time speech transcription, RAG-augmented large language model semantic understanding, and policy-compliance verification, coupled with a novel two-step caller identity authentication mechanism to ensure calling-party authenticity. It further introduces a training-free dynamic policy hot-updating mechanism enabling online, iterative refinement of security rules. Key innovations include a RAG-driven generative verification architecture and a synthetic-data-driven evaluation paradigm. Evaluated on 100 synthetic phone calls, the system achieves 97.98% accuracy and 97.44% F1-score, significantly outperforming existing state-of-the-art approaches.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Artificial Intelligence has become a double edged sword in modern society being both a boon and a bane. While it empowers individuals it also enables malicious actors to perpetrate scams such as fraudulent phone calls and user impersonations. This growing threat necessitates a robust system to protect individuals In this paper we introduce a novel real time fraud detection mechanism using Retrieval Augmented Generation technology to address this challenge on two fronts. First our system incorporates a continuously updating policy checking feature that transcribes phone calls in real time and uses RAG based models to verify that the caller is not soliciting private information thus ensuring transparency and the authenticity of the conversation. Second we implement a real time user impersonation check with a two step verification process to confirm the callers identity ensuring accountability. A key innovation of our system is the ability to update policies without retraining the entire model enhancing its adaptability. We validated our RAG based approach using synthetic call recordings achieving an accuracy of 97.98 percent and an F1score of 97.44 percent with 100 calls outperforming state of the art methods. This robust and flexible fraud detection system is well suited for real world deployment.

Problem

• Real-time Detection
• Telephonic Fraud
• Prevention System

Innovation

• Real-time Fraud Detection
• RAG-Based Language Models
• Adaptive Fraud Prevention