Deep Learning for Image Spam Detection

Abstract

Deep Learning for Image Spam Detection by Tazmina Sharmin Spam can be defined as unsolicited bulk email. In an effort to evade text-based spam filters, spammers can embed their 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 various machine learning and deep learning techniques to real-world image spam datasets, and to a challenge image spam-like dataset. We obtain results comparable to previous work for the real-world datasets, while our deep learning approach yields the best results to date for the challenge dataset. ACKNOWLEDGMENTS I would like to express my sincere gratitude to my advisor, Dr. Mark Stamp, for his extraordinary support, patience, and continuous guidance throughout my project and graduate studies as well. I would like to thank my committe members, Dr. Katerina Potika and Fabio Di Troia for being very helpful and their valuable time. My parents, Md. Gofranul Hoque and Ferdousi Rezwan, are my constant source of inspiration. I am extremely grateful for their endless support and love throughout all these years. I would like to thank my husband, Jane Alam Jan, for his gracious support and constant encouragement which made it possible. Last, but not the least, I am thankful to my daughter, Ahona, for her understanding and caring in her little own way during the past few years.