Cargando…
Fighting Deepfakes by Detecting GAN DCT Anomalies
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...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8404913/ https://www.ncbi.nlm.nih.gov/pubmed/34460764 http://dx.doi.org/10.3390/jimaging7080128 |
_version_ | 1783746232222482432 |
---|---|
author | Giudice, Oliver Guarnera, Luca Battiato, Sebastiano |
author_facet | Giudice, Oliver Guarnera, Luca Battiato, Sebastiano |
author_sort | Giudice, Oliver |
collection | PubMed |
description | 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 [Formula: see text] 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. |
format | Online Article Text |
id | pubmed-8404913 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-84049132021-10-28 Fighting Deepfakes by Detecting GAN DCT Anomalies Giudice, Oliver Guarnera, Luca Battiato, Sebastiano J Imaging Article 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 [Formula: see text] 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. MDPI 2021-07-30 /pmc/articles/PMC8404913/ /pubmed/34460764 http://dx.doi.org/10.3390/jimaging7080128 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Giudice, Oliver Guarnera, Luca Battiato, Sebastiano Fighting Deepfakes by Detecting GAN DCT Anomalies |
title | Fighting Deepfakes by Detecting GAN DCT Anomalies |
title_full | Fighting Deepfakes by Detecting GAN DCT Anomalies |
title_fullStr | Fighting Deepfakes by Detecting GAN DCT Anomalies |
title_full_unstemmed | Fighting Deepfakes by Detecting GAN DCT Anomalies |
title_short | Fighting Deepfakes by Detecting GAN DCT Anomalies |
title_sort | fighting deepfakes by detecting gan dct anomalies |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8404913/ https://www.ncbi.nlm.nih.gov/pubmed/34460764 http://dx.doi.org/10.3390/jimaging7080128 |
work_keys_str_mv | AT giudiceoliver fightingdeepfakesbydetectinggandctanomalies AT guarneraluca fightingdeepfakesbydetectinggandctanomalies AT battiatosebastiano fightingdeepfakesbydetectinggandctanomalies |