Metric Learning for Anti-Compression Facial Forgery Detection

Abstract

Detecting facial forgery images and videos is an increasingly important topic in multimedia forensics. As forgery images and videos are usually compressed into different formats such as JPEG and H264 when circulating on the Internet, existing forgery-detection methods trained on uncompressed data often suffer from significant performance degradation in identifying them. To solve this problem, we propose a novel anti-compression facial forgery detection framework, which learns a compression-insensitive embedding feature space utilizing both original and compressed forgeries. Specifically, our approach consists of three ideas: (i) extracting compression-insensitive features from both uncompressed and compressed forgeries using an adversarial learning strategy; (ii) learning a robust partition by constructing a metric loss that can reduce the distance of the paired original and compressed images in the embedding space; (iii) improving the accuracy of tampered localization with an attention-transfer module. Experimental results demonstrate that, the proposed method is highly effective in handling both compressed and uncompressed facial forgery images.

References in corpus (11)

• Auto-Encoding Variational Bayes
• MesoNet: a Compact Facial Video Forgery Detection Network
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• Exposing DeepFake Videos By Detecting Face Warping Artifacts
• Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)
• RSGAN: Face Swapping and Editing using Face and Hair Representation in Latent Spaces
• Use of a Capsule Network to Detect Fake Images and Videos
• HeadOn: Real-time Reenactment of Human Portrait Videos
• FSNet: An Identity-Aware Generative Model for Image-based Face Swapping
• Detecting GAN-generated Imagery using Color Cues
• Complement Face Forensic Detection and Localization with FacialLandmarks