Fighting deepfakes by detecting GAN DCT anomalies

Abstract

To properly contrast the Deepfake phenomenon the need to design new Deepfake detection algorithms arises; the misuse of this formidable A.I. technology brings serious consequences in the private life of every involved person. State-of-the-art proliferates with solutions using deep neural networks to detect a fake multimedia content but unfortunately these algorithms appear to be neither generalizable nor explainable. However, traces left by Generative Adversarial Network (GAN) engines during the creation of the Deepfakes can be detected by analyzing ad-hoc frequencies. For this reason, in this paper we propose a new pipeline able to detect the so-called GAN Specific Frequencies (GSF) representing a unique fingerprint of the different generative architectures. By employing Discrete Cosine Transform (DCT), anomalous frequencies were detected. The \BETA statistics inferred by the AC coefficients distribution have been the key to recognize GAN-engine generated data. Robustness tests were also carried out in order to demonstrate the effectiveness of the technique using different attacks on images such as JPEG Compression, mirroring, rotation, scaling, addition of random sized rectangles. Experiments demonstrated that the method is innovative, exceeds the state of the art and also give many insights in terms of explainability.

References in corpus (13)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Media Forensics and DeepFakes: an overview
• Unmasking DeepFakes with simple Features
• Fighting Deepfake by Exposing the Convolutional Traces on Images
• On the Spectral Bias of Neural Networks
• A Fourier Perspective on Model Robustness in Computer Vision
• Detecting and Simulating Artifacts in GAN Fake Images
• Preliminary Forensics Analysis of DeepFake Images
• FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
• Global Texture Enhancement for Fake Face Detection in the Wild
• Learning in the Frequency Domain

Cited by in corpus (9)

• Deep Learning for Deepfakes Creation and Detection: A Survey
• Combining EfficientNet and Vision Transformers for Video Deepfake Detection
• A Review of Deep Learning-based Approaches for Deepfake Content Detection
• Wavelet-Packets for Deepfake Image Analysis and Detection
• GenAI Mirage: The Impostor Bias and the Deepfake Detection Challenge in the Era of Artificial Illusions
• Detection of AI Deepfake and Fraud in Online Payments Using GAN-Based Models
• On the Exploitation of DCT-Traces in the Generative-AI Domain
• Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Images
• Além do Desempenho: Um Estudo da Confiabilidade de Detectores de Deepfakes