Media Forensics and DeepFakes: An Overview

A survey of machine learning techniques in adversarial image forensics

“…Techniques based on ML/DL-based image forensics have been great attention in recent years. Methods based on DL have consistently achieved remarkable results on a series of tasks in image forensics such as Face GAN detection , Deepfake detection ( Guarnera et al, 2020;Verdoliva, 2020 ), Coding-based detection ( Chen et al, 2008 ), and so on. Among them, CNN's are effective when dealing with various image tasks and utilized as a base for many image forensics techniques.…”

“…A number of literature surveys and reviews on the applications of ML-techniques in image forensics has been published in the literature ( Akhtar and Mian, 2018;Amodei et al, 2016;Papernot et al, 2016c;Xue et al, 2020 ;Ferreira et al, 2020;Kaur and Jindal, 2020;Verdoliva, 2020;Yang et al, 2020 ), although adversarial image forensics is generally not discussed. Amodei et al (2016) , for example, reviewed the general security concerns in artificial intelligence, particularly reinforcement learning and supervised learning algorithms.…”

Fighting Deepfake by Exposing the Convolutional Traces on Images

“…Everyone with a glimpse of experience in using Photoshop or GIMP can forge photographs in order to change their contents, the semantics and -potentially -everything. However, this kind of forgery has been widely investigated throughout recent years and commercial tools with the ability to detect and describe them are also available [1], [2]. The possibility to detect forgeries made with Photoshop or similar tools are related to the experience of the image manipulator being able to hide any kind of unrealistic artifact.…”

“…It is clear that the Deepfake phenomenon raises a serious safety issue and it is absolutely necessary to create new techniques able to detect and counteract it [1], [4]. 1 https://www.youtube.com/watch?v=SEar_6UtX9U 2 https://www.youtube.com/watch?v=gZVdPJhBkqg 3 https://www.youtube.com/watch?v=JbzVhzNaTdI 4 https://www.youtube.com/watch?v=iDM69UEyM3w 5 https://www.faceapp.com/ While detecting a Deepfake is difficult for humans, recent works have shown that they could be detected surprisingly easily by employing Convolutional Neural Networks (CNN) specifically trained on the task. However, CNN solutions presented till today, lack of robustness, generalization capability and explainability.…”

2018 Media Forensics Challenges (MFC18) :

“…These manipulations [1] can be produced by easily accessible editors (e.g., Adobe Photoshop or GIMP), and the quality of final manipulations can be very high and realistic which become challenging even for forensic analysts. With the advent of autoencoders (AE) and generative adversarial networks (GAN), such fake media (called deep fakes) also achieved a high level of realism [9,10] which drew attention in the media forensic community.…”