Weight Optimized Genetic Algorithm Driven Machine Learning Models for Robust Digital Video Watermarking Methods

Video piracy is increasing due to the standard implementation of online streaming services and storage solutions, posing significant concerns about the security of multimedia content and Intellectual Property Rights (IPR). Digital Watermarking (DW) is a revolutionary technology that enables multimedia IPR by hiding and securing intellectual property from cyberattacks. DW is now recognized as the primary point of study for data verification and IPR security measures. Watermarks are hidden tags used to detect IPR crimes and authenticate data reliability. The Least Significant Bit (LSB) to DVW is proposed to enhance data source verification, thereby increasing the possibility of reducing Mean Square Error (MSE). A Genetic Algorithm (GA) is employed to mitigate the adverse effects of LSB while enhancing the Peak Signal-to-Noise Ratio (PSNR), a crucial metric of watermarking quality. This research work employs statistical methods and experiments to analyze the difficulty of computation, accuracy, resource utilization, speed, and endurance as metrics for performance. With PSNRs exceeding 45.19 dB, the method demonstrates robustness against background noise, filtering, and video encoding. With empirical findings from experiments demonstrating a 75% Normalized Cross-Correlation (NCC), 97.89% training accuracy, and 96.78% validation accuracy, the proposed method outperforms hiding and security methods in terms of accuracy.