Chat or Trap? Detecting Scams in Messaging Applications with Large Language Models

Messaging applications have become integral to everyday communication, but their widespread use has also made them a hotbed of various scams. Cybercriminals exploit these platforms, using sophisticated social engineering techniques to deceive individuals, build trust and achieve financial gain. The advent of Generative Artificial Intelligence (GenAI) has further exacerbated the problem of scams, enabling the creation of more sophisticated and convincing fraudulent schemes. Much research has focused on detecting phishing emails and spam messages, overlooking scenarios where malicious actors initiate conversations in a way that appears harmless. This paper proposes leveraging Large Language Models (LLMs) to detect scams in chats on messaging applications. A comprehensive dataset comprising real-world scam and non-scam chat segments is constructed, followed by a thorough performance comparison of various LLMs in identifying scam indicators within chat segments. Additionally, a comparative analysis is performed between LLMs and human participants in recognizing these deceptive interactions through a detailed survey. The findings highlight the potential of LLMs to mitigate the growing threat of scams in messaging applications, thereby enhancing the security of digital communications.