Abstract:
As technology advances, the use of Generative AI to create content such as text, images, videos etc. becomes more common. This artificial intelligence-generated content a...Show MoreMetadata
Abstract:
As technology advances, the use of Generative AI to create content such as text, images, videos etc. becomes more common. This artificial intelligence-generated content appears realistic, making it difficult for humans to distinguish between AI-generated and original content because this kind of AI-generated information is manipulative and spreads false misinformation. It is vital to detect AI-generated content. This advancement not only allowed AI to generate images from existing images, but it could also make realistic, hilarious, and amazing graphics from a simple text prompt. This research aims to distinguish between synthetically created art and natural art. For this research AI-ArtBench dataset is used, which is available on the Internet. For this goal, CNN (Convolution Neural Network), VGG 19, and RESNET 50 models were built to test their ability to distinguish between AI and human art. After training several models, the best model was chosen for the task. CNN was rated as the best model, with an accuracy of 92.69%. This is a significant step forward in accurately detecting AI-generated art, which helps to reduce misinformation and manipulation of fake news in digital media. By utilizing advanced models, this research provides a tool to prevent the authenticity of artistic works in an era where people are influenced by Artificial intelligence.
Published in: 2024 Third International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)
Date of Conference: 24-26 July 2024
Date Added to IEEE Xplore: 23 October 2024
ISBN Information: