Abstract
In our civilizations, SMS continues to be an arguable communication tool despite the rattling development of protocol–predicated messaging approaches. Some businesses consider SMS as superior to e-mails for its representation. Spammers have been drawn to the pertinence of SMS for mobile phone freaks. The attacker can steal secret information by sending SMS primers to the link or directly contacting the victim. Therefore, SMS spam has generally grown in the last numberless spells with new security pitfalls parallel to SMiShing. We propose a deeper model for detecting English SMS spam communications amalgamating Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM). We also appraised other machine learning algorithms for the evaluation. The experimental findings presented in this study demonstrate that our model of CNN–LSTM exceeds other approaches with 98.40% accurateness and 98% F1-score.