用AI对抗电话诈骗，让大模型模拟受害者与骗子斗智斗勇。
Bot Wars Evolved: Orchestrating Competing LLMs in a Counterstrike Against Phone Scams
- 设计双层提示框架，让LLM自动生成真实人设并保持策略连贯。
- 在3200通诈骗对话上测试，GPT-4更自然，Deepseek更持久。
- 适合反诈研究者、安全工程师及对对抗对话感兴趣的人。
我们提出「Bot Wars」框架，利用大型语言模型（LLMs）作为诈骗诱捕者，通过模拟对抗性对话应对电话诈骗。核心贡献在于无需显式优化，仅靠思维链推理实现策略自发涌现。通过创新的两层提示架构，框架使LLM能生成符合人口统计特征的受害者人设，同时保持战略一致性。我们在一个包含3,200通诈骗对话的数据集上进行评估，该数据集经179小时真人诱捕互动验证，结果表明其能有效捕捉复杂的对抗动态。通过认知、量化和内容特定指标的系统评估显示，GPT-4在对话自然度和人设真实性方面表现更优，而Deepseek在持续互动能力上更具优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。