Explainable AI for DeepFake Detection
The surge in technological advancements has resulted in concerns over its misuse in politics and entertainment, making reliable detection methods essential. This study introduces a deepfake detection technique that enhances interpretability using the network dissection algorithm. This research consi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/725 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589219611017216 |
|---|---|
| author | Nazneen Mansoor Alexander I. Iliev |
| author_facet | Nazneen Mansoor Alexander I. Iliev |
| author_sort | Nazneen Mansoor |
| collection | DOAJ |
| description | The surge in technological advancements has resulted in concerns over its misuse in politics and entertainment, making reliable detection methods essential. This study introduces a deepfake detection technique that enhances interpretability using the network dissection algorithm. This research consists of two stages: (1) detection of forged images using advanced convolutional neural networks such as ResNet-50, Inception V3, and VGG-16, and (2) applying the network dissection algorithm to understand the models’ internal decision-making processes. The CNNs’ performance is evaluated through F1-scores ranging from 0.8 to 0.9, demonstrating their effectiveness. By analyzing the facial features learned by the models, this study provides explainable results for classifying images as real or fake. This interpretability is crucial in understanding how deepfake detection models operate. Although numerous detection models exist, they often lack transparency in their decision-making processes. This research fills that gap by offering insights into how these models distinguish real from manipulated images. The findings highlight the importance of interpretability in deep neural networks, providing a better understanding of their hierarchical structures and decision processes. |
| format | Article |
| id | doaj-art-d09399d61bb247a4a92bfd38d3950bd5 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-d09399d61bb247a4a92bfd38d3950bd52025-01-24T13:20:36ZengMDPI AGApplied Sciences2076-34172025-01-0115272510.3390/app15020725Explainable AI for DeepFake DetectionNazneen Mansoor0Alexander I. Iliev1Berlin School of Technology, SRH Berlin University of Applied Sciences, D-10587 Berlin, GermanyBerlin School of Technology, SRH Berlin University of Applied Sciences, D-10587 Berlin, GermanyThe surge in technological advancements has resulted in concerns over its misuse in politics and entertainment, making reliable detection methods essential. This study introduces a deepfake detection technique that enhances interpretability using the network dissection algorithm. This research consists of two stages: (1) detection of forged images using advanced convolutional neural networks such as ResNet-50, Inception V3, and VGG-16, and (2) applying the network dissection algorithm to understand the models’ internal decision-making processes. The CNNs’ performance is evaluated through F1-scores ranging from 0.8 to 0.9, demonstrating their effectiveness. By analyzing the facial features learned by the models, this study provides explainable results for classifying images as real or fake. This interpretability is crucial in understanding how deepfake detection models operate. Although numerous detection models exist, they often lack transparency in their decision-making processes. This research fills that gap by offering insights into how these models distinguish real from manipulated images. The findings highlight the importance of interpretability in deep neural networks, providing a better understanding of their hierarchical structures and decision processes.https://www.mdpi.com/2076-3417/15/2/725explainable artificial intelligencedeep learningdeepfake detectionexplainabilityconvolutional neural networkVGG-16 |
| spellingShingle | Nazneen Mansoor Alexander I. Iliev Explainable AI for DeepFake Detection Applied Sciences explainable artificial intelligence deep learning deepfake detection explainability convolutional neural network VGG-16 |
| title | Explainable AI for DeepFake Detection |
| title_full | Explainable AI for DeepFake Detection |
| title_fullStr | Explainable AI for DeepFake Detection |
| title_full_unstemmed | Explainable AI for DeepFake Detection |
| title_short | Explainable AI for DeepFake Detection |
| title_sort | explainable ai for deepfake detection |
| topic | explainable artificial intelligence deep learning deepfake detection explainability convolutional neural network VGG-16 |
| url | https://www.mdpi.com/2076-3417/15/2/725 |
| work_keys_str_mv | AT nazneenmansoor explainableaifordeepfakedetection AT alexanderiiliev explainableaifordeepfakedetection |