Advancements in Deepfake Technology, Biometry System and Multimedia Forensics

Dear Colleagues,

The rise of deepfakes—hyper-realistic, manipulated digital content created using deep learning—poses a serious threat to the authenticity of digital evidence. Addressing this challenge requires robust methods and interdisciplinary collaboration from multimedia forensics, biometrics, and artificial intelligence to explore advanced solutions. Key areas of focus include the development of sophisticated algorithms for detecting deepfakes across various media formats, identifying the specific tools or networks used in their creation, and investigating the vulnerabilities and countermeasures in machine learning models related to deepfake generation and detection. Additionally, the use of multimodal datasets, which capture the complex interactions between different data sources, is emphasized for more effective deepfake analysis.

Biometric security represents a critical aspect, as deepfakes can undermine the reliability of modern biometric recognition systems. This requires new detection techniques, methods for model recognition and attribution, adversarial forensics and the use of advanced datasets for multimodal analysis. The issue also explores the impact of deepfakes on biometric systems and strategies for mitigation. The potential of large language models (LLMs) in enhancing pattern recognition, data analysis, and forensic evidence interpretation, suggesting that LLMs can play a significant role in improving deepfake detection and biometric security.

The urgent threat of deepfakes could be addressed through robust forensic techniques and secure biometric systems, ultimately ensuring the authenticity and reliability of digital evidence.

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

• Creation of new algorithms for deepfake detection (image, video, audio or multimodal);
• Creation of new challenging synthetic datasets (image, video, audio or multimodal);
• Multimedia forensics: data authenticity and integrity;
• Multimedia forensics: image/video/audio forgery, detection and analysis;
• Deepfake model recognition or deepfake attribution;
• Adversarial forensics techniques on deepfake classifiers and biometric systems;
• New generative models or architectures for creating synthetic media;
• Deepfakes and biometrics;
• Ethics in data synthesis and manipulation;
• Biometric systems for authentication and verification.

Dr. Luca Guarnera
Dr. Alessandro Ortis
Dr. Giulia Orrù
Guest Editors

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.

• digital forensics
• multimedia forensics
• deepfake detection
• biometry
• adversarial forensics