Victim as a Service: Designing a System for Engaging with Interactive Scammers

TL;DR

This paper presents CHATTERBOX, an LLM-based system designed to automate long-term engagement with online scammers, enabling large-scale investigation of their tactics by simulating convincing interactions over extended periods.

Contribution

Introduction of CHATTERBOX, a novel system that automates sustained engagement with scammers using LLMs, facilitating scalable analysis of scammer behaviors and workflows.

Findings

Successfully attracted scam attempts at scale

Engaged scammers convincingly over long periods

Enabled detailed analysis of scam tactics

Abstract

Pig butchering, and similar interactive online scams, lower their victims' defenses by building trust over extended periods of conversation - sometimes weeks or months. They have become increasingly public losses (at least $75B by one recent study). However, because of their long-term conversational nature, they are extremely challenging to investigate at scale. In this paper, we describe the motivation, design, implementation, and experience with CHATTERBOX, an LLM-based system that automates long-term engagement with online scammers, making large-scale investigations of their tactics possible. We describe the techniques we have developed to attract scam attempts, the system and LLM-engineering required to convincingly engage with scammers, and the necessary capabilities required to satisfy or evade "milestones" in scammers' workflow.