Deepfake generation and detection, a survey

Deepfake refers to realistic, but fake images, sounds, and videos generated by articial intelligence methods. Recent advances in deepfake generation make deepfake more realistic and easier to make. Deepfake has been a signicant threat to national security, democracy, society, and our privacy, which calls for deepfake detection methods to combat potential threats. In the paper, we make a survey on state-ofthe-art deepfake generation methods, detection methods, and existing datasets. Current deepfake generation methods can be classified into face swapping and facial reenactment. Deepfake detection methods are mainly based features and machine learning methods. There are still some challenges for deepfake detection, such as progress on deepfake generation, lack of high quality datasets and benchmark. Future trends on deepfake detection can be efficient, robust and systematical detection methods and high quality datasets.

Automated summary

This paper surveys the state-of-the-art deepfake generation methods, detection methods, and existing datasets. Deepfake generation methods are classified into face swapping and facial reenactment, while detection methods mainly rely on features and machine learning. Challenges for deepfake detection include advancements in deepfake generation, lack of high quality datasets and benchmarks. Future trends in deepfake detection involve the development of efficient, robust, and systematic detection methods and the availability of high quality datasets.