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.
@article{arxiv.2510.23927,
title = {Victim as a Service: Designing a System for Engaging with Interactive Scammers},
author = {Daniel Spokoyny and Nikolai Vogler and Xin Gao and Tianyi Zheng and Yufei Weng and Jonghyun Park and Jiajun Jiao and Geoffrey M. Voelker and Stefan Savage and Taylor Berg-Kirkpatrick},
journal= {arXiv preprint arXiv:2510.23927},
year = {2025}
}