The demand for trustworthy ways to identify altered or morphed videos has increased due to the abundance of multimedia information on the internet. Deep learning algorithms have made it possible to approach this problem in novel ways this study uses recurrent neural networks (RNN) and long short-term memory (LSTM) to provide a novel method for the detection of altered films the suggested methodology makes use of the movie’s temporal and sequential properties to spot morphing or tampering attempts. To start, preprocess the video frames, extract the important features, and then convert them into a format that can be used as input for the LSTM and RNN models. These recurrent neural networks were selected because of their capacity to record temporal relationships and patterns, which are necessary for spotting minor changes.