Year: 2025
Type: preprint
Abstract: We present "Bot Wars," a framework using Large Language Models (LLMs) scam-baiters to counter phone scams through simulated adversarial dialogues. Our key contribution is a formal foundation for strategy emergence through chain-of-thought reasoning without explicit optimization. Through a novel two-layer prompt architecture, our framework enables LLMs to craft demographically authentic victim personas while maintaining strategic coherence. We evaluate our approach using a dataset of 3,200 scam dialogues validated against 179 hours of human scam-baiting interactions, demonstrating its effectiveness in capturing complex adversarial dynamics. Our systematic evaluation through cognitive, quantitative, and content-specific metrics shows that GPT-4 excels in dialogue naturalness and persona authenticity, while Deepseek demonstrates superior engagement sustainability.
Source: arXiv (Cornell University)
Authors: Basta, Nardine, Atkins, Conor, Kaafar, Dali
Language: English
Topic: Spam and Phishing Detection
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979336152
Cites:
Cited by:
Related to: