Convolutional neural networks for image spam detection
Publication Date
5-3-2020
Document Type
Article
Publication Title
Information Security Journal: A Global Perspective
Volume
29
Issue
3
DOI
10.1080/19393555.2020.1722867
First Page
103
Last Page
117
Abstract
Spam can be defined as unsolicited bulk e-mail. In an effort to evade text-based filters, spammers sometimes embed spam text in an image, which is referred to as image spam. In this research, we consider the problem of image spam detection, based on image analysis. We apply convolutional neural networks (CNN) to this problem, we compare the results obtained using CNNs to other machine learning techniques, and we compare our results to previous related work. We consider both real-world image spam and challenging image spam-like datasets. Our results improve on previous work by employing CNNs based on a novel feature set consisting of a combination of the raw image and Canny edges.
Keywords
Convolutional neural network, image spam, multilayer perceptron, support vector machine
Department
Computer Science
Recommended Citation
Tazmina Sharmin, Fabio Di Troia, Katerina Potika, and Mark Stamp. "Convolutional neural networks for image spam detection" Information Security Journal: A Global Perspective (2020): 103-117. https://doi.org/10.1080/19393555.2020.1722867
