Deepfakes, hyper-realistic synthetic media created using artificial intelligence, pose a growing threat to trust in information and online interactions, serious challenge to the integrity of digital content. This paper delves into the evolving landscape of deepfake detection. Our primary objectives are analyzing the techniques used to detect fake videos, tracing their development alongside the advancements in deep learning that enable increasingly sophisticated deepfakes, assessing societal impact by investigating the social, political, and psychological implications of deepfakes. This includes exploring how they can manipulate public perception and potentially disrupt societal harmony and evaluating detection methods used for fake video detection. Through a comparative analysis, we evaluate their effectiveness, identify limitations, and highlight potential areas for improvement. By examining both the detection methods and the evolving nature of deepfakes, this paper aims to provide a comprehensive understanding of this critical challenge. Through this analysis, we hope to contribute to the development of more robust solutions for identifying and mitigating the negative impacts of deepfakes. Finally, we are trying to contribute to a deeper understanding of the dynamic challenges posed by deepfake videos and inform strategies to fortify the digital ecosystem against malicious content.