DeepFake MNIST+: A DeepFake Facial Animation Dataset

TL;DR

This paper introduces DeepFake MNIST+, a new facial animation dataset designed to challenge existing DeepFake detection and liveness detection methods by providing 10,000 animated videos with various actions and qualities.

Contribution

The paper presents a novel dataset for facial animation DeepFakes, generated with a state-of-the-art animator, to improve detection of animated DeepFake videos and assess current defenses.

Findings

Existing datasets are insufficient for developing reliable detection methods.

Current liveness detectors can be spoofed by the new dataset.

Detection difficulty varies with motion type and compression quality.

Abstract

The DeepFakes, which are the facial manipulation techniques, is the emerging threat to digital society. Various DeepFake detection methods and datasets are proposed for detecting such data, especially for face-swapping. However, recent researches less consider facial animation, which is also important in the DeepFake attack side. It tries to animate a face image with actions provided by a driving video, which also leads to a concern about the security of recent payment systems that reply on liveness detection to authenticate real users via recognising a sequence of user facial actions. However, our experiments show that the existed datasets are not sufficient to develop reliable detection methods. While the current liveness detector cannot defend such videos as the attack. As a response, we propose a new human face animation dataset, called DeepFake MNIST+, generated by a SOTA image animation generator. It includes 10,000 facial animation videos in ten different actions, which can spoof the recent liveness detectors. A baseline detection method and a comprehensive analysis of the method is also included in this paper. In addition, we analyze the proposed dataset's properties and reveal the difficulty and importance of detecting animation datasets under different types of motion and compression quality.