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

Abstract

Spam, typically unwanted material, can manifest in various forms, including images. While numerous machine learning techniques excel in detecting textual spam, they often falter when it comes to identifying image-based spam. This paper introduces a novel framework designed specifically for identifying image spams. Images are categorized into two groups: spam images, containing undesirable material, and ham images, encompassing everything else. In this paper, a novel technique based on CNN and gated recurrent unit (GRU) for image spam detection has been proposed. Our proposed methodology hinges on the utilization of diverse pre-trained deep learning models, such as InceptionV3, DenseNet121 (Densely Connected Convolutional Networks 121), ResNet50 (Residual Networks), VGG16 (Visual Geometry Group), and MobileNetV2, to effectively filter out unwanted spam images. We evaluate the performance of our approach using different Dataset. Additionally, we address the challenge of limited labeled data by leveraging transfer learning and employing data augmentation techniques. Experimental results demonstrate the efficacy of our proposed model, achieving impressive accuracy levels while maintaining computational efficiency, with testing times ranging from one to two seconds for the challenge dataset.