Abstract: In the present generation, social media is a big advantage for an individual to grow. On the other hand, we can’t neglect the fact that the it’s a huge platform for negativity too. With the rapid progress of recent years, techniques that generate and manipulate multimedia content can now provide a very advanced level of realism. The boundary between real and synthetic media has become very thin. On the one hand, this opens the door to a series of exciting applications in different fields such as creative arts, advertising, film production, video games. On the other hand, it poses enormous security threats. Software packages freely available on the web allow any individual, without special skills, to create very realistic fake images and videos. These techniques can be used to manipulate public opinion regarding anything and create chaos. In this paper, we would like to overview few major facts and figures regarding exceeding image forgery techniques that exists and propose a better way on how to detect these forgeries and fakes.

Keywords: GAN, ELA, deep learning, convolutional neural networks, Fake colorized image detection.

| DOI: 10.17148/IJIREEICE.2021.9107