Previous research has focused on spam/ham detection for SMS, but I want to narrow my research down to ham/phish in SMS, as there is a slight nuiance with spam and phishing based texts.
I will be using publically available datasets that have labelled data for ham/spam/phish.
https://www.kaggle.com/datasets/galactus007/sms-smishing-collection-data-set
https://www.kaggle.com/datasets/taruntiwarihp/phishing-site-urls
The plan is to narrow down my research to a particular context, such as SMS detection for chatGPT generated SMS, and I also plan to add more features to the machine learning model, such as URL analysis and natural language processing.
https://www.kaggle.com/code/akanksha496/spam-detection-using-tensorflow/notebook