The recent revolution in generative models has thrust upon us the imminent danger of deepfakes, which can offer unprecedented levels of increasingly realistic manipulated images and video. Even more worrying is the fact that – while in the past, video forgery was associated with a slow, painstaking process usually reserved for experts – currently, deepfake-related manipulation technologies are streamlined to be used by essentially everyone with the will to manipulate reality. Deepfakes pose an imminent security threat to us all, and to date, deepfakes are able to mislead face recognition systems, as well as humans.
This special issue will provide a forum to solicit research addressing the assessment of media integrity.
In particular, the focus of this special issue will be on data-driven approaches using machine learning.
The topics of interest for the special issue include, but are not limited to:
- Deepfake detection approaches,
- Deepfake countermeasures including digital signatures, watermarking or other integrity mechanisms,
- Datasets for image and video manipulation,
- Detection and manipulation techniques in digital documents,
- Detection and manipulation techniques in scene images,
- Encryption in digital manipulation,
- Forensics and IoT in digital manipulation,
- Digital manipulation and adversarial attacks,
- Image and video synthesis, image and video generation and prediction,
- Accountability of forensics techniques,
- Multimedia authorship attribution,
- Social impact of Deepfakes,
- Deepfake Retrieval: retrieval from databases deep image manipulations,
- Fairness, Accountability and Transparency in ML-based Forensics Methods
Submission deadline: 15 December 2022
Lead Guest Editor
Antitza Dantcheva, Inria
Abhijit Das, Birla Institute of Technology and Science, Pilani (BITS Pilani)
Hu Han, Institute of Computing Technology, Chinese Academy of Sciences, China
Christian Rathgeb, Department of Computer sciences, Hochschule Darmstadt, Germany
Naser Damer,Fraunhofer Institute for Computer Graphics Research IGD, Darmstadt, Germany
Luisa Verdoliva, University Federico II of Naples, Italy
Ruben Tolosana,Universidad Autonoma de Madrid, Madrid, Spain
Important: Authors should select "Manipulation Detection in Digital Images and Videos" when they reach the “Article Type” step in the submission system.