An Independent Discriminant Network Towards the Identification of Counterfeit Images and Videos

Open Webpage

Shayantani Kar, B. Shresth Bhimrajka, Aditya Kumar, Sahil Gupta, Sourav Ghosh, Subhamita Mukherjee, Shauvik Paul

Published: 28 May 2025, Last Modified: 16 Oct 2025CrossrefEveryoneRevisionsCC BY-SA 4.0
Abstract: Rapid spread of false images and videos on online platforms is an emerging problem. Anyone may add, delete, clone, or modify people and entities from an image using various editing software which are readily available. This generates false and misleading proof to hide the crime. Nowadays, these false and counterfeit images and videos are flooding the internet. These spread false information. Many methods are available in the literature for detecting counterfeit content, but new methods of counterfeiting are also evolving. Generative Adversarial Network (GAN) is an effective method as it modifies the context and definition of images, producing plausible results via image-to-image translation. This work uses an independent discriminant network that can identify GAN-generated images or videos. A discriminant network has been created using a convolutional neural network based on InceptionResNetV2. The article also proposes a platform where users can detect forged images and videos. This proposed work can help the forensics domain detect counterfeit videos and hidden criminal evidence toward the identification of criminal activities.