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

2025-10-27

AI Summary

To address the challenge of scaling empirical investigation of interactive online scams (e.g., “pig-butchering” fraud), this paper introduces CHATTERBOX: the first large language model (LLM)-based automated long-term adversarial dialogue framework. Methodologically, it integrates dialogue state tracking, emotion-aware behavioral simulation, decoy account deployment, and dynamic detection of critical scam milestones to faithfully emulate victim behavior and deliver interpretable, intervenable responses throughout the end-to-end scam lifecycle. In real-world network deployments, CHATTERBOX successfully lured, sustained, and monitored multiple active scam conversations—achieving, for the first time, large-scale, proactive, and closed-loop empirical investigation of interactive fraud. Experimental evaluation confirms its high behavioral fidelity, robustness against adversarial variations, and practical deployability. This work establishes a novel paradigm for anti-fraud technology, shifting from reactive defense to proactive attribution and intervention.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Adversarial Agents
• Natural Language Processing: Conversational AI/Dialog Systems

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

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.

Problem

• Automating long-term engagement with interactive online scammers
• Enabling large-scale investigation of conversational scam tactics
• Developing techniques to attract and sustain scammer interactions

Innovation

• LLM-based system automates long-term scammer engagement
• Developed techniques to attract and respond to scammers
• Satisfies scammer workflow milestones for realistic interaction