"It Warned Me Just at the Right Moment": Exploring LLM-based Real-time Detection of Phone Scams

TL;DR

This paper presents a real-time detection framework using large language models to identify phone scams during calls, aiming to warn users immediately and reduce financial and psychological harm.

Contribution

It introduces a novel LLM-based approach for modeling scam calls and assessing fraudulent intent in real-time, advancing scam detection technology.

Findings

The method achieves high precision in detecting scams.

Analysis of trade-offs between detection speed and accuracy.

Refined model improves detection performance.

Abstract

Despite living in the era of the internet, phone-based scams remain one of the most prevalent forms of scams. These scams aim to exploit victims for financial gain, causing both monetary losses and psychological distress. While governments, industries, and academia have actively introduced various countermeasures, scammers also continue to evolve their tactics, making phone scams a persistent threat. To combat these increasingly sophisticated scams, detection technologies must also advance. In this work, we propose a framework for modeling scam calls and introduce an LLM-based real-time detection approach, which assesses fraudulent intent in conversations, further providing immediate warnings to users to mitigate harm. Through experiments, we evaluate the method's performance and analyze key factors influencing its effectiveness. This analysis enables us to refine the method to improve precision while exploring the trade-off between recall and timeliness, paving the way for future directions in this critical area of research.