A Survey on Image Forgery Detection Techniques Using Machine Learning Approaches

Vartika  Sharma; Madhurya  M.J.; Ashutosh  Dhavan A.; Kushi  T.G.; Diya  P.B.

Abstract

With the advent of newer technologies and usage of data in various service fields like education, commercial and healthcare, etc. The possibility of tampering and altering the data in the form of media like images is easily seen to derive various illegitimate benefits and outcomes. The rapid advancements in technology and the increased utilization of data in various service sectors such as education, commerce, healthcare, etc., have raised concerns about the possibility of data tampering and image manipulation for illicit gains. This can result in a loss of data integrity and have significant repercussions. In smart healthcare frameworks, new communication technologies, features, and facilities are being developed with the goal of providing easy-to-use, accurate, and real-time healthcare services to clients. Given the sensitive nature of health-related data, it is imperative to prioritize security and caution in order to ensure seamless and real-time system operations. A new approach for detecting image forgery, utilizing deep learning techniques, particularly convolutional neural networks (CNNs), has been created to identify fraudulent medical images. This method employs CNNs for detecting image forgery and ensuring the authenticity of medical images.

Abstract

Keywords