Application of error level analysis in image spam classification using deep learning model

Abstract

Image spam is a type of spam that contains text information inserted in an image file. Traditional classification systems based on feature engineering require manual extraction of certain quantitative and qualitative image features for classification. However, these systems are often not robust to adversarial attacks. In contrast, classification pipelines that use convolutional neural network (CNN) models automatically extract features from images. This approach has been shown to achieve high accuracies even on challenge datasets that are designed to defeat the purpose of classification. We propose a method for improving the performance of CNN models for image spam classification. Our method uses the concept of error level analysis (ELA) as a pre-processing step. ELA is a technique for detecting image tampering by analyzing the error levels of the image pixels. We show that ELA can be used to improve the accuracy of CNN models for image spam classification, even on challenge datasets. Our results demonstrate that the application of ELA as a pre-processing technique in our proposed model can significantly improve the results of the classification tasks on image spam datasets.

Multilayer Perceptron’s Neural Network Based Image Spam Detection on Social Media

“…The "Convolutional Neural Network (CNN)" architectures employed in this research follow a sequential design, incorporating convolutional and max-pooling layers for feature extraction and spatial down sampling [25]. The first CNN model consists of four convolutional layers with increasing filter sizes (32, 64, 128, and 256), each followed by ReLU activation and max-pooling operations [23].…”

“…There are two main approaches to employing 'transfer learning' [25]:Utilizing the pretrained model as a 'feature extractor' and incorporating a new classifier for the task at hand [26].Employing the pretrained model for finetuning (FT), which involves adjusting the parameters of both the new fully connected (FC) layers of the classifier and specific convolutional layers of the CNN through selective unfreezing.…”