ScamGPT-J: Inside the Scammer's Mind, A Generative AI-Based Approach Toward Combating Messaging Scams

Abstract: The increase in global cellphone usage has led to a spike in instant messaging scams, causing extensive socio-economic damage with yearly losses exceeding half a trillion US dollars. These scams pose a challenge to the integrity of justice systems worldwide due to their international nature, which complicates legal action. Scams often exploit emotional vulnerabilities, making detection difficult for many. To address this, we introduce ScamGPT-J, a LLM that replicates scammer tactics. Unlike traditional methods that simply detect and block scammers, ScamGPT-J helps users recognize scam interactions by simulating scammer responses in real-time. If a user receives a message that closely matches a ScamGPT-J simulated response, it signals a potential scam, thus helping users identify and avoid scams more effectively. The model's effectiveness is evaluated through technical congruence with scam dialogues and user engagement. Our results show that ScamGPT-J can significantly aid in protecting against messaging scams.