Social Network Identification through Image Classification with CNN

To further advance the development of this area, we propose a novel framework, called FusionNET, that integrates two established convolutional neural networks (CNNs). Identification of the source social network based on the downloaded images is an important multimedia forensic task with significant cyber security implications in light of the sheer volume of images and videos shared across various social media platforms. 

The separately learned features are then fused by the FusionNET to inform the ensuing source identification or source oriented image classification component. A series of experiments were conducted on a number of image datasets across various SNs and instant messaging apps to validate the feasibility of the FusionNET.