GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection

Abstract

The availability of large-scale facial databases, together with the remarkable progresses of deep learning technologies, in particular Generative Adversarial Networks (GANs), have led to the generation of extremely realistic fake facial content, raising obvious concerns about the potential for misuse. Such concerns have fostered the research on manipulation detection methods that, contrary to humans, have already achieved astonishing results in various scenarios. In this study, we focus on the synthesis of entire facial images, which is a specific type of facial manipulation. The main contributions of this study are four-fold: i) a novel strategy to remove GAN "fingerprints" from synthetic fake images based on autoencoders is described, in order to spoof facial manipulation detection systems while keeping the visual quality of the resulting images; ii) an in-depth analysis of the recent literature in facial manipulation detection; iii) a complete experimental assessment of this type of facial manipulation, considering the state-of-the-art fake detection systems (based on holistic deep networks, steganalysis, and local artifacts), remarking how challenging is this task in unconstrained scenarios; and finally iv) we announce a novel public database, named iFakeFaceDB, yielding from the application of our proposed GAN-fingerprint Removal approach (GANprintR) to already very realistic synthetic fake images. The results obtained in our empirical evaluation show that additional efforts are required to develop robust facial manipulation detection systems against unseen conditions and spoof techniques, such as the one proposed in this study.

References in corpus (16)

• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Spectral Normalization for Generative Adversarial Networks
• Learning Face Representation from Scratch
• Media Forensics and DeepFakes: an overview
• DeepFakes: a New Threat to Face Recognition? Assessment and Detection
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• The Deepfake Detection Challenge (DFDC) Preview Dataset
• Biometric Presentation Attack Detection: Beyond the Visible Spectrum
• Detecting GAN-generated Imagery using Color Cues
• BioTouchPass2: Touchscreen Password Biometrics Using Time-Aligned Recurrent Neural Networks
• Detecting GAN generated Fake Images using Co-occurrence Matrices
• Detecting and Simulating Artifacts in GAN Fake Images
• Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
• FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
• Detecting Photoshopped Faces by Scripting Photoshop
• Source Generator Attribution via Inversion

Cited by in corpus (3)

• Media Forensics and DeepFakes: an overview
• Detection, Attribution and Localization of GAN Generated Images
• Adversarial Attacks on Co-Occurrence Features for GAN Detection