Deepfakes, Fake News and Multimedia Manipulation from Generation to Detection (Volume II)

Dear Colleagues,

Machine-learning-based techniques are being utilized to generate hyper-realistic manipulated facial multimedia content known as DeepFakes. While such technologies have positive potentials for use in entertainment applications, the malevolent use of this technology can harm citizens and society as a whole by facilitating the construction of indecent content, the spread of fake news to subvert elections or undermine politics, bullying, and the amelioration of social engineering to perpetrate financial fraud. In fact, it has been shown that manipulated facial multimedia content can deceive not only humans but also automated face-recognition-based biometric systems. The advent of advanced hardware, powerful smart devices, user-friendly apps (e.g., FaceApp and ZAO), and open-source ML codes (e.g., Generative Adversarial Networks) has enabled even non-experts to effortlessly create manipulated facial multimedia contents. In principle, face manipulation involves swapping two faces, modifying facial attributes (e.g., age and gender), morphing two different faces into one face, adding imperceptible perturbations (i.e., adversarial examples), synthetically generating faces, or animating/recreating facial expressions in face images/videos.

Topics of interest in this Special Issue include but are not limited to:

• The generation of DeepFakes, face morphing, manipulation, and adversarial attacks;
• The generation of synthetic faces using ML/AI techniques, e.g., GANs;
• The detection of DeepFakes, face morphing, manipulation, and adversarial attacks, including generalizable systems;
• The generation and detection of audio DeepFakes;
• Novel datasets and experimental protocols to facilitate research in DeepFakes and face manipulations;
• The formulation and extraction of DeepFake devices, platforms, and software/app fingerprints;
• Face recognition systems (and humans) against DeepFakes, face morphing, manipulation, and adversarial attacks, including their vulnerabilities to digital face manipulations;
• DeepFakes in the courtroom and on copyright law.

Dr. Zahid Akhtar
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• Deepfakes
• digital face manipulations
• digital forensics
• fake news
• multimedia manipulations
• generative AI
• security and privacy
• information authenticity
• face morphing attack
• biometrics