AI-BASED FACIAL DE-IDENTIFICATION FOR CHILDREN'S DIGITAL PRIVACY
DOI:
https://doi.org/10.47080/m11eck75Abstract
Social media has become an inseparable part of daily life in today's digital era. Many parents frequently share photos of their children online, exposing them to risks related to privacy and security. This research addresses such issues by developing an Android-based facial de-identification application that utilises the YOLOv8 algorithm to protect minors' privacy. The methodology involves several stages: data collection, pre-processing, model training, and application development. The dataset includes over 2,889 images of children, which were augmented to enhance its size and diversity. YOLOv8, a state-of-the-art object detection algorithm, was trained with these images to achieve high precision and recall in identifying children's faces. The developed application integrates the YOLOv8 model within a user-friendly interface built with Flutter. Results indicate that YOLOv8 effectively detects children's faces with a high precision of 95%, accuracy of 88%, recall of 92%, and mAP50 of 0.977. While the model demonstrates strong performance on training data, there is room for improvement on unseen data. By leveraging YOLOv8 and providing an accessible mobile application, the work allows parents to protect their children's identities online. The application mitigates risks of unauthorised use and exploitation of children's images by enabling facial de-identification, thus promoting safer online practices for families.
References
Annur, C. M. (2023). Jumlah Pengguna Instagram Indonesia Terbanyak ke-4 di Dunia. Databooks. https://databoks.katadata.co.id/teknologi-telekomunikasi/statistik/f38041b68c2f889/jumlah-pengguna-instagram-indonesia-terbanyak-ke-4-di-dunia
Ardiansyah, A., Qodri, K., Banna, D., & Al-Baihaqi, M. (2024). Pemanfaatan Sam dan Yolov8 Untuk Deteksi dan Segmentation MRI Tumor Otak. TEKNIMEDIA: Teknologi Informasi Dan Multimedia, 5, 82–89. https://doi.org/10.46764/teknimedia.v5i1.192
Chumachenko, K., Gabbouj, M., & Iosifidis, A. (2022). Chapter 11 - Object detection and tracking (A. Iosifidis & A. B. T.-D. L. for R. P. and C. Tefas (Eds.); pp. 243–278). Academic Press. https://doi.org/https://doi.org/10.1016/B978-0-32-385787-1.00016-6
Endra, Y., & Ratri, D. D. M. (2021). Foto Bayi Artis Dicatut dalam Sindikat Jual Beli Anak, Audi Marissa Marah! Matamata. https://www.matamata.com/seleb/2021/09/05/195718/foto-bayi-artis-dicatut-dalam-sindikat-jual-beli-anak-audi-marissa-marah?ref=detail-terkini-2#.
Fahrezi, M., & Widiyanto, E. (2024). Implementasi YOLOv8 Dalam Penghitung Masuk Dan Keluar Manusia Pada Gedung. JATISI (Jurnal Teknik Informatika Dan Sistem Informasi), 11, 335–345.
Gyawali, D., Pokharel, P., Chauhan, A., & Shakya, S. C. (2020). Age Range Estimation Using MTCNN and VGG-Face Model. 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 1–6. https://doi.org/10.1109/ICCCNT49239.2020.9225443
Hari Dunia Anti Perdagangan Orang 2024, Menteri PPPA: Lawan dan Akhiri Segala Bentuk Perdagangan Orang. (2024). KemenPPPA. https://www.kemenpppa.go.id/page/view/NTMzNQ%3D%3D?
Hari Dunia Anti Perdagangan Orang 2024. (2024). IOM UN Migration Indonesia. https://indonesia.iom.int/id/news/hari-dunia-anti-perdagangan-orang-2024-menciptakan-lingkungan-migrasi-yang-aman-untuk-melawan-perdagangan-orang
Kim, J., Sung, J.-Y., & Park, S. (2020). Comparison of Faster-RCNN, YOLO, and SSD for Real-Time Vehicle Type Recognition. 2020 IEEE International Conference on Consumer Electronics - Asia (ICCE-Asia), 1–4. https://doi.org/10.1109/ICCE-Asia49877.2020.9277040
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Livingstone, S., Blum-Ross, A., & Zhang, D. (2024). What do parents think, and do, about their children’s online privacy? https://eprints.lse.ac.uk/87954/1/Livingstone_Parenting Digital Survey Report 3_Published.pdf
Maulana, I., Rahaningsih, N., & Suprapti, T. (2024). Analisis Penggunaan Model Yolov8 (You Only Look Once) Terhadap Deteksi Citra Senjata Berbahaya. Jati, 7(6), 3621–3627. https://doi.org/10.36040/jati.v7i6.8271
Mustapha, M. F., Mohamad, N. M., Osman, G., & Ab Hamid, S. H. (2021). Age Group Classification using Convolutional Neural Network (CNN). Journal of Physics: Conference Series, 2084(1), 012028. https://doi.org/10.1088/1742-6596/2084/1/012028
Permana, R., Saldu, H., & Maulana, D. I. (2022). Optimasi Image Classification Pada Jenis Sampah Dengan Data Augmentation dan Convolutional Neural Network. J.Sist.Inf.Inform., 5(2), 111–120. https://doi.org/10.47080/simika.v5i2.1913
Rahaditya Kusuma, N. T., I Made Agus Dwi Suarjaya, & Vihikan, W. O. (2024). Implementasi Metode YOLOv8 Pada Mobile Apps Untuk Klasifikasi Kain Endek Bali. Decode, 4(3), 787–797. https://doi.org/10.51454/decode.v4i3.610
Rasjid, A. A., Rahmat, B., & Sihananto, A. N. (2024). Implementasi YOLOv8 Pada Robot Deteksi Objek. Journal of Technology and System Information, 1(3), 9. https://doi.org/10.47134/jtsi.v1i3.2969
Setiyadi, A., Utami, E., & Ariatmanto, D. (2023). Analisa Kemampuan Algoritma YOLOv8 Dalam Deteksi Objek Manusia Dengan Metode Modifikasi Arsitektur. J-SAKTI (Jurnal Sains Komputer & Informatika), 7(2). https://tunasbangsa.ac.id/ejurnal/index.php/jsakti/article/view/694
Sharma, N. (2023). Understanding and Applying F1 Score: AI Evaluation Essentials with Hands-On Coding Example. Arize. https://arize.com/blog-course/f1-score/
Solawetz, J. (2020). What is Mean Average Precision (mAP) in Object Detection? Roboflow. https://blog.roboflow.com/mean-average-precision/
Srivastava, S., Divekar, A. V., Anilkumar, C., Naik, I., Kulkarni, V., & Pattabiraman, V. (2021). Comparative analysis of deep learning image detection algorithms. Journal of Big Data, 8(1), 66. https://doi.org/10.1186/s40537-021-00434-w
Takase, Y. (2023). Introducing YoloV8: Operation and comparison to previous versions of the object detection model. RevComm Tech Blog. https://tech.revcomm.co.jp/yolov8-introduction-en
Terven, J. R., & Esparza, D. M. C. (2023). A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond. ArXiv, abs/2304.00501. https://api.semanticscholar.org/CorpusID:257913644
Thaneeshan, R., Thanikasalam, K., & Pinidiyaarachchi, A. (2022). Gender and Age Estimation From Facial Images using Deep Learning. 2022 7th International Conference on Information Technology Research (ICITR), 1–6. https://doi.org/10.1109/ICITR57877.2022.9993277
Ting, K. M. (2010). Confusion Matrix. In C. Sammut & G. I. Webb (Eds.), Encyclopedia of Machine Learning (p. 209). Springer US. https://doi.org/10.1007/978-0-387-30164-8_157
United Nation Office on Drugs and Crime. (2024). United Nations. https://www.unodc.org/unodc/en/press/releases/2024/December/unodc-global-human-trafficking-report_-detected-victims-up-25-per-cent-as-more-children-are-exploited-and-forced-labour-cases-spike.html
Wisak, S. A., Safirah, N. A., & Kaesmetan, Y. R. (2024). Identifikasi Jenis Mangga Berdasarkan Ciri Daun Menggunakan Metode CNN. J.Sist.Inf.Inform., 7(2), 121–129. https://doi.org/10.47080/simika.v7i2.3295
Zhang, Y.-J. (2023). Computer Vision Overview. In Y.-J. Zhang (Ed.), 3-D Computer Vision: Principles, Algorithms and Applications (pp. 1–35). Springer Nature Singapore. https://doi.org/10.1007/978-981-19-7580-6_1
