Deepfake is a technology dedicated to creating highly realistic facial images and videos under specific conditions, which has significant application potential in fields such as entertainment, movie production, digital human creation, to name a few. With the advancements in deep learning, techniques primarily represented by Variational Autoencoders and Generative Adversarial Networks have achieved impressive generation results. More recently, the emergence of diffusion models with powerful generation capabilities has sparked a renewed wave of research. In addition to deepfake generation, corresponding detection technologies continuously evolve to regulate the potential misuse of deepfakes, such as for privacy invasion and phishing attacks. This survey comprehensively reviews the latest developments in deepfake generation and detection, summarizing and analyzing current state-of-the-arts in this rapidly evolving field. We first unify task definitions, comprehensively introduce datasets and metrics, and discuss developing technologies. Then, we discuss the development of several related sub-fields and focus on researching four representative deepfake fields: face swapping, face reenactment, talking face generation, and facial attribute editing, as well as forgery detection. Subsequently, we comprehensively benchmark representative methods on popular datasets for each field, fully evaluating the latest and influential published works. Finally, we analyze challenges and future research directions of the discussed fields.

翻译：深度伪造是一种致力于在特定条件下生成高度逼真的人脸图像与视频的技术，在娱乐、电影制作、数字人创建等领域具有重要应用潜力。随着深度学习的发展，以变分自编码器和生成对抗网络为代表的技术取得了令人瞩目的生成效果。近期，具备强大生成能力的扩散模型的出现引发了新一轮研究浪潮。除深度伪造生成外，相应的检测技术也在持续演进，以规范深度伪造可能引发的滥用行为，例如隐私侵犯和网络钓鱼攻击。本综述全面梳理了深度伪造生成与检测领域的最新进展，总结并分析了这一快速演进领域中的前沿技术。我们首先统一任务定义，系统介绍数据集与评估指标，并探讨技术发展趋势。随后，我们讨论多个相关子领域的发展，重点研究四个代表性深度伪造方向：换脸、面部重演、说话人脸生成、面部属性编辑，以及伪造检测。在此基础上，我们在各方向的公开数据集上对代表性方法进行全面的基准测试，充分评估最新且具有影响力的已发表成果。最后，我们分析了这些方向面临的挑战与未来研究方向。