基于卷积长短期记忆网络的换脸视频检测

Exposing Deep Fake Video Detection Based on Convolutional Long Short-Term Memory Network

随着近年假脸合成技术(DeepFake)的发展,当前社交平台充斥着通过换脸技术生成的海量假视频,虽然假视频可以丰富大众的娱乐生活,但是同样存在着曝光隐私等负面问题。如何精准检测出由DeepFake生成的伪造数据已成为网络安全防御领域中一项重要且具有挑战性的任务。针对这一问题,很多科研工作者提出了针对换脸视频的检测方法,但是现有的检测方法均忽略了DeepFake视频帧与帧之间的关联特性。因此,对于部分针对脸部信息进行平滑处理的篡改方法,已有的检测方法的检测准确率有明显的下降。基于此,提出了一种基于长短期记忆(LSTM)网络的DeepFake视频检测算法。该算法能够捕获DeepFake视频帧中的脸部微表情变化,并利用编码器生成局部视觉信息的特征,同时利用注意力机制实现局部信息的权重分配;最后再次借助LSTM网络实现时序空间下视频帧的关联信息融合,从而实现对DeepFake视频数据的有效检测。采用FaceForensics++数据库对所提算法进行了评估,与现有方法相比,实验结果证明了所提算法的优越性。

With the advancement of Deep Fake technology in recent years, the current social platform is full of massive fake videos produced by face-changing technology. Although fake videos can enrich people’s entertainment, they also have disadvantages, such as exposing their personal information. How to accurately detect the fake data generated by Deep Fake technology has become an important and difficult task in network security defense. Many researchers have proposed face-changing video detection methods in response to this problem, but the existing detection methods often ignore the incoherence of facial feature crossing video frames. Thus, they are easily countered by optimizing facial synthesizing techniques, resulting in accuracy degradation. Based on this, we propose a novel Deep Fake detection method based on long short-term memory(LSTM) network that captures the micro expression changes in terms of the facial features caused by the composite video and uses an encoder to generate features of local visual information. Simultaneously, the attention mechanism is used to achieve the weight distribution of local information. Finally, the LSTM network is used to realize the association information fusion of video frames in temporal space, resulting in the effective detection of Deep Fake video data. This paper evaluates a proposed algorithm on the Face Frensics+o + dataset, and when compared to existing methods, the experimental results show that the proposed algorithm is superior.