Combating SMS Attacks Using Deeplearning with Embedding Technique

Phishing is a cyber-attack where personal information is stolen through email, phone,or text.Smishing,a kind of phishing, involves using Short Message Service (SMS) for cyber-attacks. People are more likely to provide personal information like account details and passwords when receiving SMS messages, employed in stealing cash or confidential information from persons or firms, making smishing a critical issue. The project aims to design a robust system using Deep Learning(DL)techniques to accurately predict spam or ham SMS messages. A comprehensive dataset of labeled SMS messages is collected and pre-processed to ensure high-quality input data. Deep learning models like LSTM, Rnn, Bi-LSTM, and GRU are trained using word embedding techniques like TF-IDF, count vectorizer, and GloVe. The optimal model is chosen based on performance measures like accuracy, precision, recall, F1-score, and AUC-ROC, which are then fine-tuned for resilient functioning and executed using a scalable approach.