(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 13, No. 12, 2022 301 | Page www.ijacsa.thesai.org Recognition of Copy Move Forgeries in Digital Images using Hybrid Optimization and Convolutional Neural Network Algorithm Anna Gustina Zainal 1 , Dr. Chamandeep Kaur 2 , Dr. Mohammed Saleh Al Ansari 3 , Ricardo Fernando Cosio Borda 4 , Dr.A. Nageswaran 5 , Rasha M. Abd El-Aziz 6 Department of Communication, University of Lampung, Indonesia 1 Lecturer, Department of IT, Jazan University, Saudi Arabia 2 Associate Professor, College of Engineering-Department of Chemical Engineering, University of Bahrain, Bahrain 3 Universidad Privada del Norte, Peru 4 Professor, Department of CSE. Sri Venkateswaraa College of Technology, Vadakkal village, Sriperumbudur- 602105 5 Department of Computer Science-College of Science and Arts in Qurayyat, Jouf University, Saudi Arabia 6 Faculty of Computers and Information, Assiut University, Assiut, Egypt 6 Abstract—In the modern day, protecting data against tampering is a significant task. One of the most common forms of information display has been digital photographs. Images may be exploited in a variety of contexts, including the military, security applications, intelligence areas, legal evidence, social media, and journalism. Digital picture forgeries involve altering the original images with strange patterns, which result in variability in the image's characteristics. Among the most challenging forms of image forgeries to identify is Copy Move Forgery (CMF). It occurs by copying a portion or piece of the picture and then inserting it again, but in a different place. When the actual content is unavailable, techniques for detecting fake content have been utilised in image security. This study presents a novel method for Copy Move Forgery Recognition (CMFR), which is mostly based on deep learning (DL) and hybrid optimization. The hybrid Grey Wolf Optimization and African Buffalo Optimization (GWO-ABO) using Convolution Neural Network (CNN) technique i.e., GWO-ABO-CNN is the foundation of the suggested model. The developed model extracts the features of images by convolution layers, and pooling layers; hereafter, the features are matched and detect CMF. The MICC-F220, SATs- 130, and MICC-F600 datasets were three publicly accessible datasets to which this methodology has been implemented. To assess the model's efficacy, the outcomes of implementing the GWO-ABO-CNN model were contrasted with those of other approaches. Keywords—Copy move forgery; convolutional neural network; image authentication; deep learning; tampered images I. INTRODUCTION Today's technological images play a crucial role in a broad range of fields. They are used in a variety of uses in the fields of broadcasting, journalism, medicine, and the army, to name a very few. The computerised image can be seen as a notable resource of information in today's advanced globe due to the advancement in the technology of sophisticated picture, such as sensors, coding, and Computers, as well as the widespread usage of the internet [1]. In addition, advanced image forgery refers to the intentional manipulation of a digitized image in order to change the conceptual interpretation of the contextual perspective contained within. Also, with availability of cutting-edge information structures editing tools like Photoshop, it becomes quite simple to create sophisticated fakes from one or more images. The reliability of photographs plays a crucial role in a variety of fields, such as measurement analysis, criminal probe, surveillance systems, organisational learning, medical imaging, and media broadcasting. Creating phony pictures is a specialty with a lengthy tradition. But in the current technology age, it showed out to be very simple to change the facts talked to by an image without any obvious consequences. One of the most widely popular techniques for altering digital photographs is copy-move. One of two factors can explain why there are copy regions in an image: first, the proximity of two particles or objects that are identical in size, form, and colouring; one of them may be a copy of the other one. Second, the appearance of duplicate regions in the results is caused by the proximity of a reasonably massive area with one colour and similar in features, such as foundational principles sky, splitter, etc. Copy-move forgeries is created by copying and pasting a region or sector from one spot in an image to some other spot inside the same picture in order to modify or hide one or more objects and create a false vision. Moreover, copy-move forgeries identification is known to be successful when using key point-based analysis. There were some changes made to the image during copy-move forgeries. Moreover, to implement quality impersonating forgeries, techniques including turning, cropping, lightening, reduction, and force and contribute are used. Nowadays, even a non- expert may easily produce convincing forgeries in digital images because of modern digital imaging and robust image manipulation tools. Huge different forgeries have been created in recent decades as a result of digital manipulation, which involves incorporating or removing certain parts from the image. Thus, checking the materials of digital photos or discovering fraudulent areas would be immediately helpful, for example, when images are used as evidence at trial.