cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota sorong,
Papua barat
INDONESIA
Insect (Informatics and Security): Jurnal Teknik Informatika
Published by Universitas Muhammadiyah Sorong
ISSN : 24769010     EISSN : 2614431X     DOI : -
Core Subject : Science,
Computer Science & IT
Insect (Informatics Engineering Journal) is a scientific journal which prioritizes the publication of articles related to informatics and Security issues that deal with informatics and security issues such as information technique, network and others. This is an opened-journal where everyone can submit their articles, as long as they are original, unpublished and not under review for possible publication in other journals. insect Journal is biannual publication issued in the month of October and March.
Arjuna Subject : -
Articles 11 Documents
 1   2 
Search results for , issue "Vol. 11 No. 2 (2025): Oktober 2025" : 11 Documents clear
XceptionNet-based Digital Image Forensics with DFRWS Framework for Deepfake Detection Akbar, Muh. Hajar Akbar; Jimsan, Jimsan; Yahya, Yahya; Ilcham, Ilcham; Nasrullah, Nasrullah
Insect (Informatics and Security): Jurnal Teknik Informatika Vol. 11 No. 2 (2025): Oktober 2025
Publisher : Universitas Muhammadiyah Sorong

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33506/insect.v11i2.4996

Abstract

This study presents a novel approach to deepfake detection by integrating the DFRWS (Digital Forensics Research Workshop) framework with a deep learning architecture based on XceptionNet. The rapid advancement of deepfake technology poses a significant threat to digital media authenticity, necessitating robust and reliable detection methods. In this work, we implement a fine-tuned XceptionNet model enhanced with additional regularization techniques, specifically focusing on facial feature analysis. The model is trained on a balanced dataset comprising 2,000 images, equally divided between authentic and deepfake samples. Experimental results demonstrate exceptional performance, achieving an accuracy of 91.25%, precision of 88.73%, recall of 94.50%, and an AUC score of 0.9710. The proposed model shows a significant improvement in detecting subtle manipulation artifacts while maintaining computational efficiency, offering a promising solution for practical deepfake identification in real-world scenarios.

Page 2 of 2 | Total Record : 11

 1   2 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 11 No. 2 (2025): Oktober 2025 Vol. 11 No. 1 (2025): Maret 2025 Vol. 10 No. 2 (2024): Oktober 2024 Vol. 10 No. 1 (2024): Maret 2024 Vol. 9 No. 1 (2023): Oktober 2023 Vol. 8 No. 2 (2023): Maret 2023 Vol. 8 No. 1 (2022): Oktober 2022 Vol. 7 No. 2 (2022): Maret 2022 Vol 7, No 1 (2021): Oktober 2021 Vol. 7 No. 1 (2021): Oktober 2021 Vol. 6 No. 2 (2021): Maret 2021 Vol 6, No 2 (2021): Maret 2021 Vol 6, No 1 (2020): Oktober 2020 Vol. 6 No. 1 (2020): Oktober 2020 Vol 5, No 2 (2020): Maret 2020 Vol. 5 No. 2 (2020): Maret 2020 Vol 5, No 1 (2019): Oktober 2019 Vol. 5 No. 1 (2019): Oktober 2019 Vol. 4 No. 2 (2019): Maret 2019 Vol 4, No 2 (2019): Maret 2019 Vol 4, No 1 (2018): Oktober 2018 Vol. 4 No. 1 (2018): Oktober 2018 More Issue