Towards Explainable Deep Learning with Attention Mechanisms for Fake Image Detection

Citation

Lau, Suen Kei and Chua, Sook Ling and Foo, Lee Kien (2025) Towards Explainable Deep Learning with Attention Mechanisms for Fake Image Detection. Frontiers in Artificial Intelligence and Applications. pp. 55-61. ISSN 09226389

[img] Text
FAIA-404-FAIA250106.pdf - Published Version
Restricted to Repository staff only

Download (2MB)

Abstract

The proliferation of fake images on the internet has become increasingly alarming. Advanced techniques including generative adversarial networks can generate visually real images that can mislead people and create false information. This poses a threat and can cause serious impacts. Many methods based on deep learning were proposed to detect fake images. These methods have demonstrated ability to achieve highly accurate results in detecting fake images. However, due to its “black-box” nature, there is a lack of explainability of the decision-making process in these models. In this paper, we integrate the convolution block attention module in ResNet-18 to improve the explainability of the deep learning model for fake image detection. The results showed that our method achieved a higher performance compared to the baseline method.

Item Type: Article
Uncontrolled Keywords: Explainable deep learning, fake image detection, attention, convolutional neural network
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 01 Jul 2025 01:11
Last Modified: 01 Jul 2025 01:11
URII: http://shdl.mmu.edu.my/id/eprint/14195

Downloads

Downloads per month over past year

View ItemEdit (login required)