Graph-Based Spam Image Detection for Mobile Phone Spam Image Filtering

Graph-Based Spam Image Detection for Mobile Phone Spam Image Filtering

So Yeon Kim (Department of Information and Computer Engineering, Ajou University, Suwon, South Korea) and Kyung-Ah Sohn (Department of Information and Computer Engineering, Ajou University, Suwon, South Korea)
Copyright: © 2015 |Pages: 15
DOI: 10.4018/IJSI.2015100106
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Spam images in mobile phones have increasingly appeared these days. As the spam filtering systems become more sophisticated, spams are being more intelligent. Although detection of email-spams has been quite successful, there have not been effective solutions for detecting mobile phone spams yet, especially, spam images. In addition to the expensive image processing time, insufficient spam image data in mobile phones makes it challenging to train a general model. To address this issue, the authors propose a graph-based approach that utilizes graph structure in abundant e-mail spam dataset. The authors employ different clustering algorithms to find a subset of e-mail spam images similar to phone spam images. Furthermore, the performance behavior with respect to different image descriptors of Pyramid Histogram of Visual Words (PHOW) and RGB histogram is extensively investigated. The authors' results highlight that the proposed idea is fairly meaningful in increasing training data size, thus effectively improving image spam detection performance.
Article Preview

Spam filtering algorithm is proposed in many different kinds of media. Especially, spam images are widely spread in e-mail or on the web. Many machine learning approaches are proposed for e-mail spam image filtering (Biggio, Fumera, Pillai, & Roli, 2011; Guzella & Caminhas, 2009). As there is abundant spam text in e-mail and spam filtering system can therefore capture the spam text very well, image spams are rapidly increased. Image analysis such as OCR (Optical Character Recognition) is conducted for embedded images in e-mail (Fumera, Pillai, & Roli, 2006). Rather than computationally expensive OCR processing, many approaches which train the features of spam images are proposed (Aradhye, Myers, & Herson, 2005; Nhung & Phuong, 2007; Wakade, Liszka, & Chan, 2013). For advanced feature extraction techniques, artificial neural networks are used (Soranamageswari & Meena, 2010). In (Al-Duwairi, Khater, & Al-Jarrah, 2011), image texture analysis-based image spam filtering algorithm is newly proposed which uses low-level image texture features. In these works, using image features also showed the desirable performance rather than using expensive OCR techniques.

In (Mahajan & Slaney, 2010), they proposed image spam classification model fusing image, text and web-graph features to handle the spam images on the web. For automatic spam image identification, (Cheng, Deng, Fu, Wang, & Qin, 2011) proposed a graph-based spectral semi-supervised feature selection algorithm to handle redundant features also. It showed that graph features of spam images have positive impact on spam image filtering.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 5: 4 Issues (2017)
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing