SISTEM DETEKSI GAMBAR DEEPFAKE MENGGUNAKAN CNN DENSENET-121 DENGAN WATERMARKING LEAST SIGNIFICANT BIT (LSB)
DOI:
https://doi.org/10.70248/jrsit.v2i3.1939Keywords:
Deepfake, DenseNet-121, CNN, LSB Watermarking, Deteksi Pemalsuan CitraAbstract
Penelitian ini bertujuan untuk mengembangkan model deteksi deepfake menggunakan arsitektur Convolutional Neural Network (CNN) DenseNet-121 serta mengevaluasi efektivitas teknik watermarking Least Significant Bit (LSB) dalam meningkatkan keamanan citra digital. Dataset yang digunakan terdiri dari citra asli dan citra deepfake yang diperoleh dari sumber terbuka Kaggle, yang dibagi menjadi subset pelatihan, validasi, dan pengujian dengan total 22.382 gambar. Proses preprocessing melibatkan resizing ke ukuran 128x128 piksel, konversi ke grayscale, normalisasi, serta augmentasi data untuk meningkatkan generalisasi model. Model DenseNet-121 dikompilasi menggunakan optimizer Adam dan loss function categorical crossentropy, dengan evaluasi menggunakan metrik akurasi, precision, recall, dan F1-score. Hasil pelatihan menunjukkan bahwa model mampu mendeteksi deepfake dengan akurasi tinggi. Selain itu, evaluasi watermarking menggunakan PSNR menunjukkan bahwa penyisipan watermark dengan metode LSB tidak mengurangi kualitas visual citra secara signifikan. Penelitian ini memberikan kontribusi dalam meningkatkan deteksi deepfake dan keamanan digital melalui kombinasi metode CNN dan watermarking.
Kata Kunci: Deepfake, CNN, DenseNet-121, Watermarking, LSB, Deteksi Citra Digital
References
A C, P., & M T, S. (2023). An Overview on Research Trends, Challenges, Applications and Future Direction in Digital Image Watermarking. International Research Journal on Advanced Science Hub, 5(01), 8–14. https://doi.org/10.47392/irjash.2023.002
Almars, A. M. (2021). Deepfakes detection techniques using deep learning: a survey. Journal of Computer and Communications, 9(05), 20–35.
Alzahrani, A. (2024). Digital Image Forensics: An Improved DenseNet Architecture for Forged Image Detection. Engineering, Technology and Applied Science Research, 14(2), 13671–13680. https://doi.org/10.48084/etasr.7029
Begum, M., & Uddin, M. S. (2020). Digital image watermarking techniques: A review. Information (Switzerland), 11(2). https://doi.org/10.3390/info11020110
Boato, G., Conotter, V., De Natale, F. G. B., & Fontanari, C. (2009). Watermarking robustness evaluation based on perceptual quality via genetic algorithms. IEEE Transactions on Information Forensics and Security, 4(2), 207–216. https://doi.org/10.1109/TIFS.2009.2020362
Bose, S., Madhulika, Acharjee, S., Chowdhury, S. R., Chakraborty, S., & Dey, N. (2014). Effect of watermarking in vector quantization based image compression. 2014 International Conference on Control, Instrumentation, Communication and Computational Technologies, ICCICCT 2014, December, 503–508. https://doi.org/10.1109/ICCICCT.2014.6993014
Chopra, D. (2012). Lsb Based Digital Image Watermarking For Gray Scale Image. IOSR Journal of Computer Engineering, 6(1), 36–41. https://doi.org/10.9790/0661-0613641
Faheem, Z. Bin, Ali, M., Raza, M. A., Arslan, F., Ali, J., Masud, M., & Shorfuzzaman, M. (2022). Image Watermarking Scheme Using LSB and Image Gradient. Applied Sciences (Switzerland), 12(9), 1–12. https://doi.org/10.3390/app12094202
Karnouskos, S. (2020). Artificial Intelligence in Digital Media: The Era of Deepfakes. IEEE Transactions on Technology and Society, 1(3), 138–147. https://doi.org/10.1109/tts.2020.3001312
Khan, S. A., & Dang-Nguyen, D.-T. (2023). Deepfake Detection: A Comparative Analysis. 1(1), 1–28.
License, C. A., & Rizvee, M. M. (2023). Retracted : Comparative Analysis of Deepfake Image Detection. 2021. https://doi.org/10.1155/2021/3111676
Masood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023). Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward. Applied Intelligence, 53(4), 3974–4026. https://doi.org/10.1007/s10489-022-03766-z
Memon, N., & Wong, P. W. (1998). Protecting Digital Media Content. Communications of the ACM, 41(7), 35–43. https://doi.org/10.1145/278476.278485
Parthasarathy, C., & Nagar, J. (2009). Increased Robustness of Lsb Audio Steganography By Reduced Distortion Lsb. Audio.
Patel, Y., Tanwar, S., Bhattacharya, P., Gupta, R., Alsuwian, T., Davidson, I. E., & Mazibuko, T. F. (2023). An Improved Dense CNN Architecture for Deepfake Image Detection. IEEE Access, 11(March), 22081–22095. https://doi.org/10.1109/ACCESS.2023.3251417
Sanivarapu, P. V., Rajesh, K. N. V. P. S., & Hosny, K. M. (2022). applied sciences Digital Watermarking System for Copyright Protection and Authentication of Images Using Cryptographic Techniques.
Setiawati, I., Hermanto, M. T., & Ujianto, E. (2023). Digital Watermarking Implementation Of Digital Watermarking On Images Using The Least Significant Bit Method. International Journal of Engineering Technology and Natural Sciences, 5(1), 10–18. https://doi.org/10.46923/ijets.v5i1.191
Subramanyam, A. V., Emmanuel, S., & Kankanhalli, M. S. (2012). Robust watermarking of compressed and encrypted JPEG2000 images. IEEE Transactions on Multimedia, 14(3 PART 2), 703–716. https://doi.org/10.1109/TMM.2011.2181342
Swaminathan, A., Mao, Y., & Wu, M. (2006). Robust and secure image hashing. IEEE Transactions on Information Forensics and Security, 1(2), 215–230. https://doi.org/10.1109/TIFS.2006.873601
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020). Deepfakes and beyond: A Survey of face manipulation and fake detection. Information Fusion, 64, 131–148. https://doi.org/10.1016/j.inffus.2020.06.014
Wan, W., Wang, J., Zhang, Y., Li, J., Yu, H., & Sun, J. (n.d.). A Comprehensive Survey on Robust Image Watermarking A R T I C L E I N F O. 1–26.
