Abstract
Deepfakes, which are driven by developments in generative AI, seriously jeopardize public trust, cybersecurity, and the veracity of information. This study offers a comprehensive analysis of the most recent methods for creating and detecting deepfakes in image, video, and audio modalities. With a focus on their advantages and disadvantages in cross-dataset and real-world scenarios, we compile the latest developments in transformer-based detection models, multimodal biometric defenses, and Generative Adversarial Networks (GANs). We provide implementation-level information such as pseudocode workflows, hyperparameter settings, and preprocessing pipelines for popular detection frameworks to improve reproducibility. We also examine the implications of cybersecurity, including identity theft and biometric spoofing, as well as policy-oriented solutions that incorporate federated learning, explainable AI, and ethical protections. By enriching technical insights with interdisciplinary perspectives, this review charts a roadmap for building robust, scalable, and trustworthy deepfake detection systems.