On the Detection of Digital Face Manipulation

Detecting manipulated facial images and videos is an increasingly important topic in digital media forensics. As advanced synthetic face generation and manipulation methods become available, new types of fake face representations are being created and raise significant concerns for their implications in social media. Hence, it is crucial to detect the manipulated face image and locate manipulated facial regions. Instead of simply using a multi-task learning approach to simultaneously detect manipulated images and predict the manipulated mask (regions), we propose to utilize the attention mechanism to process and improve the feature maps of the classifier model. The learned attention maps highlight the informative regions to further improve the binary classification power, and also visualize the manipulated regions. In addition, to enable our study of manipulated facial images detection and localization, we have collected the first database which contains numerous types of facial forgeries. With this dataset, we perform a thorough analysis of data-driven fake face detection. We demonstrate that the use of an attention mechanism improves manipulated facial region localization and fake detection.