Synthetic Data for Scam Detection: Leveraging LLMs to Train Deep Learning Models
21
Issued Date
2024-01-01
Resource Type
Scopus ID
2-s2.0-105007152224
Journal Title
Proceedings 2024 IEEE Wic International Conference on Web Intelligence and Intelligent Agent Technology Wi Iat 2024
Start Page
868
End Page
873
Rights Holder(s)
SCOPUS
Bibliographic Citation
Proceedings 2024 IEEE Wic International Conference on Web Intelligence and Intelligent Agent Technology Wi Iat 2024 (2024) , 868-873
Suggested Citation
Gumphusiri P., Triyason T. Synthetic Data for Scam Detection: Leveraging LLMs to Train Deep Learning Models. Proceedings 2024 IEEE Wic International Conference on Web Intelligence and Intelligent Agent Technology Wi Iat 2024 (2024) , 868-873. 873. doi:10.1109/WI-IAT62293.2024.00141 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/110613
Title
Synthetic Data for Scam Detection: Leveraging LLMs to Train Deep Learning Models
Author(s)
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
This paper presents a novel approach to training scam detection models using synthetic data generated by Large Language Models (LLMs). We propose single-agent and multi-agent methods for data generation and train six deep learning architectures-LSTM, BiLSTM, GRU, BiGRU, CNN, and BERT-to classify conversations as scam or non-scam. Our experiments demonstrate that models trained on synthetic data achieve high accuracy on both generated test sets and real-world scam conversations. The models perform well even with limited conversation turns and when analyzing only the suspect's messages, indicating potential for early scam detection and privacy-preserving applications. Our findings highlight the efficacy of synthetic data in overcoming real-world dataset limitations for scam detection. We make the dataset and trained models publicly available to facilitate further research and development in this critical area of fraud prevention.