Saealal, Muhammad Salihin and Ibrahim, Mohd. Zamri and Shapiai, Mohd. Ibrahim and Fadilah, Norasyikin (2023) In-The-Wild deepfake detection using adaptable CNN models with visual class activation mapping for improved accuracy. In: 5th International Conference on Computer Communication and the Internet, ICCCI, 23 June 2023-25 June 2023, Fujisawa, Japan.
Full text not available from this repository.
Official URL: http://dx.doi.org/10.1109/ICCCI59363.2023.10210096
Abstract
Deepfake technology has become increasingly sophisticated in recent years, making detecting fake images and videos challenging. This paper investigates the performance of adaptable convolutional neural network (CNN) models for detecting Deepfakes. In-the-wild OpenForensics dataset was used to evaluate four different CNN models (DenseNet121, ResNet18, SqueezeNet, and VGG11) at different batch sizes and with various performance metrics. Results show that the adapted VGG11 model with a batch size of 32 achieved the highest accuracy of 94.46% in detecting Deepfakes, outperforming the other models, with DenseNet121 as the second-best performer achieving an accuracy of 93.89% with the same batch size. Grad-CAM techniques are utilized to visualize the decision-making process within the models, aiding in understanding the Deepfake classification process. These findings provide valuable insights into the performance of different deep learning models and can guide the selection of an appropriate model for a specific application.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Uncontrolled Keywords: | batch size, convolution neural network, deep learning, deepfake, Grad-CAM visualization |
Subjects: | T Technology > T Technology (General) |
Divisions: | Malaysia-Japan International Institute of Technology |
ID Code: | 107616 |
Deposited By: | Widya Wahid |
Deposited On: | 25 Sep 2024 06:40 |
Last Modified: | 25 Sep 2024 06:40 |
Repository Staff Only: item control page