An evolutionary- convolutional neural network for fake image detection
release_nsi2qynxn5cttewx4soreus4su
by
Retaj Matroud Jasim, tayseer Salman
2023 Volume 29, p1657
Abstract
<span lang="EN-US">The fast development in deep learning techniques, besides the wide spread of social networks, facilitated fabricating and distributing images and videos without prior knowledge. This paper developed an evolutionary learning algorithm to automatically design a convolutional neural network (CNN) architecture for deepfake detection. Genetic algorithm (GA) based on residual network (ResNet) and densely connected convolutional network (DenseNet) as building block units for feature extraction versus multilayer perceptron (MLP), random forest (RF) and support vector machine (SVM) as classifiers generates different CNN structures. A local search mutation operation proposed to optimize three layers: (batch normlization, activation function, and regularizes). This method has the advantage of working on different datasets without preprocessing. Findings using two datasets evidence the efficiency of the suggested approach where the generated models outperform the state-of-art by increasing 1% in the accuracy; this confirms that intuitive design is the new direction for better generalization.</span>
In application/xml+jats
format
Archived Files and Locations
application/pdf 670.4 kB
file_43orpbxv4fei7dmbo5w64bxmou
|
ijeecs.iaescore.com (publisher) web.archive.org (webarchive) |
article-journal
Stage
published
Date 2023-03-01
access all versions, variants, and formats of this works (eg, pre-prints)
Crossref Metadata (via API)
Worldcat
SHERPA/RoMEO (journal policies)
wikidata.org
CORE.ac.uk
Semantic Scholar
Google Scholar