Fighting deepfakes by detecting GAN DCT anomalies

TL;DR

This paper introduces a novel method for detecting GAN-generated Deepfakes by analyzing unique frequency anomalies using DCT and statistical analysis, improving accuracy and explainability over existing techniques.

Contribution

The paper presents a new pipeline that detects GAN-specific frequency fingerprints with DCT and statistical analysis, enhancing Deepfake detection robustness and explainability.

Findings

Effective detection of GAN Deepfakes using frequency analysis

Method outperforms existing state-of-the-art techniques

Robust against common image manipulations like JPEG, rotation, and scaling

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.