Hybrid Features by Combining Visual and Text Information to Improve Spam Filtering Performance

Abstract

The development of information and communication technology has created many positive outcomes, including convenience for people; however, cases of unsolicited communication, such as spam, also occur frequently. Spam is the indiscriminate transmission of unwanted information by anonymous users, called spammers. Spam content is indiscriminately transmitted to users in various forms, such as SMS, e-mail, and social network service posts, causing negative experiences for users of the service, while also creating costs, such as unnecessarily large amounts of network traffic. In addition, spam content includes phishing, hype or false advertising, and illegal content. Recently, spammers have also used images that contain stimulating content to effectively attract users’ curiosity and attention. Image spam contains more complex information than text, making it more difficult to analyze and to generalize its properties compared to text. Therefore, existing text-based spam detectors are vulnerable to spam image attacks, resulting in a decline in service quality. In this paper, a “hybrid features by combining visual and text information to improve spam filtering performance” method is proposed to reduce the occurrence of misclassification. The proposed method employs three sub-models to extract features from spam images and a classifier model to output the results using the features. Each sub-model extracts topic-, word-, and image-embedding-based features from spam images. In addition, the sub-models use optical character recognition, latent Dirichlet allocation, and word2Vec techniques to extract features from images. To evaluate spam image classification performance, the spam classifiers were trained using the extracted features and the results were measured using a confusion matrix. Our model achieved an accuracy of 0.9814 and a macro-F1 score of 0.9813. In addition, the application of OCR evasion techniques resulted in a decrease in recognition performance. Using the proposed model, a mean macro-F1 score of 0.9607 was obtained.