|
Abstract: |
Phishing threats, especially those sent via SMS (known as smishing), are a big worry in the digital world. So better ways are needed to fight against phishing because cybercriminals keep changing their tactics. This study aims to make the online systems safer by using advanced technology called deep learning , specifically a method called the AlexNet-LSTM algorithm, to sort out smishing messages effectively. Phishing vulnerability depends on different things such as age, gender, how much time someone spends online, and how stressed they are. In this study, deep learning is used to find SMS threats, and different types of text-based attacks are figured out by using the AlexNet-LSTM algorithm. To evaluate the superiority of this new method and how well it performs, it is compared with traditional methods such as logistic regression, random forest, and support vector machine. The results show a big improvement in accuracy, up to 99.6%, proving the efficacy of deep learning to make the online systems safer against various tricky attacks. |
Key words: cyber security system phishing attack classification deep learning |
DOI:10.11916/j.issn.1005-9113.2023126 |
Clc Number:TP393 |
Fund: |