E-mail Fraud Detection
Arju Kumar1, Saurav Kumar2, Kishan Kumar3, Bharat Bhushan Naib4
1Arju Kumar, Department of Computer Science and Engineering, SCSE, Galgotias University, Greater Noida (U.P), India.
2Saurav Kumar, Department of Computer Science and Engineering, SCSE, Galgotias University, Greater Noida (U.P), India.
3Kishan Kumar, Department of Computer Science and Engineering, SCSE, Galgotias University, Greater Noida (U.P), India.
4Dr. Bharat Bhushan Naib, Department of Computer Science and Engineering, SCSE, Galgotias University, Greater Noida (U.P), India.
Manuscript received on 03 June 2023 | Revised Manuscript received on 23 July 2023 | Manuscript Accepted on 15 August 2023 | Manuscript published on 30 August 2023 | PP: 1-7 | Volume-11 Issue-9, August 2023 | Retrieval Number: 100.1/ijese.B77970712223 | DOI: 10.35940/ijese.B7797.0811923
Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Spam issues have become worse on social media platforms and apps with the growth of IoT. To address the problem, researchers have proposed several spam detection techniques. Spam rates are still high despite the use of anti-spam technologies and tactics, especially given the ubiquity of rogue emails that lead to dangerous websites. By consuming memory or storage space, spam emails can cause servers to run slowly. One of the most effective methods for identifying and eliminating spam is email filtering. To this end, various deep learning and machine learning technologies have been used, including Naive Bayes, decision trees, SVM, and random forest. Email and Internet of Things spam filters employ various machine learning approaches, and these systems are categorised in this research. Additionally, as more people use mobile devices and SMS services become more affordable, the issue of spam SMS messages is spreading worldwide. This study suggests using a variety of machine learning approaches to detect and eliminate spam as a solution to this problem. According to the trial findings, the TF-IDF with the Random Forest classification algorithm outperformed the other examined algorithms in terms of accuracy. It is only possible to gauge performance on accuracy since the dataset is imbalanced. Therefore, the algorithms must have good precision, recall, and Fmeasure.
Keywords: Convolutional Neural Network (CNN), Onyx Model, Deep Learning, MXNet, TensorFlow, and Face Recognition.
Scope of the Article: Deep Learning