Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Creating deepfake multimedia, and especially deepfake videos, has become much easier these days due to the availability of deepfake tools and the virtually unlimited numbers of face images found online. Research and industry communities have dedicated time and resources to develop detection methods to expose these fake videos. Although these detection methods have been developed over the past few years, synthesis methods have also made progress, allowing for the production of deepfake videos that are harder and harder to differentiate from real videos. This research paper proposes an improved optical flow estimation-based method to detect and expose the discrepancies between video frames. Augmentation and modification are experimented upon to try to improve the system's overall accuracy. Furthermore, the system is trained on graphics processing units (GPUs) and tensor processing units (TPUs) to explore the effects and benefits of each type of hardware in deepfake detection. TPUs were found to have shorter training times compared to GPUs. VGG-16 is the best performing model when used as a backbone for the system, as it achieved around 82.0% detection accuracy when trained on GPUs and 71.34% accuracy on TPUs.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9002804 | PMC |
| http://dx.doi.org/10.3390/s22072500 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Sexualized Deepfake Abuse: Perpetrator and Victim Perspectives on the Motivations and Forms of Non-Consensually Created and Shared Sexualized Deepfake Imagery.
J Interpers Violence
September 2025
Goldsmiths, University of London, London, United Kingdom.
Advances in digital technologies provide new opportunities for harm, including sexualized deepfake abuse-the non-consensual creation, distribution, or threat to create/distribute an image or video of another person that had been altered in a nude or sexual way. Since 2017, there has been a proliferation of shared open-source technologies to facilitate deepfake creation and dissemination, and a corresponding increase in cases of sexualized deepfake abuse. There is a substantive risk that the increased accessibility of easy-to-use tools, the normalization of non-consensually sexualizing others, and the minimization of harms experienced by those who have their images created and/or shared may impact prevention and response efforts.
View Article and Find Full Text PDFHybrid Convolutional Neural Network and Generative Adversarial Network Framework for Robust Deepfake Detection: Advancing Accuracy, Scalability, and Multimodal Integration.
J Vis Exp
August 2025
Department of Computer Science and Engineering, Gokaraju Rangaraju Institute of Engineering and Technology, Hyderabad, India.
Deepfakes pose critical threats to digital media integrity and societal trust. This paper presents a hybrid deepfake detection framework combining Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) to address challenges in scalability, generalizability, and adversarial robustness. The framework integrates adversarial training, a temporal decay analysis model, and multimodal detection across audio, video, and text domains.
View Article and Find Full Text PDFArtificial intelligence-generated deepfakes in healthcare and biomedical research: major adverse implications for patients, public and professionals.
Intern Med J
September 2025
Baker Heart and Diabetes Institute, Melbourne, Victoria, Australia.
False advertising is a long-term problem, but, with modern technology, it is now possible to create rapidly and inexpensively and widely distribute fake video, audio and written social media presentations attributed to people without their knowledge or permission. Such 'deepfake' videos and other promotional material, allegedly by healthcare and biomedical research experts, are increasingly being used, often encouraging the purchase of a product that is not scientifically validated, and with which the expert is not associated. We describe some of our recent experiences and suggest potential actions.
View Article and Find Full Text PDFFairForensics: mitigating attribute bias in deepfake detection by integrating texture and attribute features.
Neural Netw
July 2025
State Key Laboratory of Integrated Services Networks, School of Electronic Engineering, Xidian University, Xi'an, 710071, Shaanxi, PR China. Electronic address:
With the rapid advancement of artificial intelligence, Deepfake technology, which involves the synthesis of highly realistic face-swapping images and videos, has garnered significant attention. While this technology has various legitimate applications, its misuse in political manipulation, identity fraud, and misinformation poses serious societal risks. Consequently, effective face forgery detection methods are crucial.
View Article and Find Full Text PDFA Dual-Branch Fusion Model for Deepfake Detection Using Video Frames and Microexpression Features.
J Imaging
July 2025
Centre for Research and Technology Hellas, 57001 Thessaloniki, Greece.
Deepfake detection has become a critical issue due to the rise of synthetic media and its potential for misuse. In this paper, we propose a novel approach to deepfake detection by combining video frame analysis with facial microexpression features. The dual-branch fusion model utilizes a 3D ResNet18 for spatiotemporal feature extraction and a transformer model to capture microexpression patterns, which are difficult to replicate in manipulated content.
View Article and Find Full Text PDF