Pemanfaatan Fingerprint Multi-Hash Ensemble dengan Mekanisme Veto untuk Mitigasi Fraud AI Berbasis Blockchain
DOI:
https://doi.org/10.30865/jurikom.v15i5.9732Keywords:
AI-generated image, multi-hash ensemble, perceptual hashing, blockchain, veto mechanism, image integrity verification, IPFSAbstract
Proliferasi gambar hasil generasi AI seperti DALL-E, Midjourney, dan Stable Diffusion telah menciptakan ancaman serius terhadap autentikasi visual di berbagai platform digital. Kemampuan AI generatif dalam menghasilkan gambar fotorealistik membutuhkan pendekatan verifikasi yang robust dan efisien untuk memitigasi penyalahgunaan konten visual. Penelitian ini mengusulkan framework Multi-Hash Ensemble yang mengintegrasikan dua pendekatan fingerprinting, yaitu Full Image Hash Ensemble dan Hybrid Fingerprint dengan ROI Extraction, yang diperkuat oleh Veto Mechanism berbasis gradient signature, Local Binary Pattern (LBP), distribusi warna, dan shape descriptor, serta arsitektur blockchain on-chain/off-chain untuk menjamin keimutabelan data. Evaluasi dilakukan pada dataset 200 citra dari kategori face dan nature dengan 22.847 perbandingan melalui tiga skenario pengujian. Metode 1 (Full Image Hash Ensemble) menghasilkan True Acceptance Rate (TAR) 94,15%, True Rejection Rate (TRR) 98,97%, akurasi 98,43%, F1-Score 93,03%, dan Equal Error Rate (EER) 3,44%. Metode 2 (Hybrid Fingerprint) mencapai akurasi 96,71%, FAR terendah 0,68%, dan FAR nol pada mode HYBRID_ENSEMBLE untuk seluruh 3.486 pasangan imposter. Analisis sensitivitas threshold pada Metode 2 menunjukkan titik optimal pada 0,22 dengan F1-Score 85,18% dan akurasi 96,92%. Kedua metode menunjukkan ketahanan sempurna terhadap kompresi JPEG dan resize, namun memiliki kelemahan pada serangan Crop 10%. Dari aspek efisiensi blockchain, arsitektur hibrida on-chain/off-chain berhasil mereduksi data penyimpanan dari citra 2–5 MB menjadi hanya 64 byte per registrasi (rasio kompresi >99,99%), dengan estimasi biaya Gas Fee < $0,01 USD per citra pada jaringan Layer-2 (Polygon dan Arbitrum). Keimutabelan data off-chain dijamin melalui Content Hash SHA-256 yang dikunci pada blockchain, sehingga manipulasi data dapat dideteksi secara otomatis. Temuan ini menunjukkan bahwa framework yang diusulkan memberikan keseimbangan optimal antara akurasi deteksi, efisiensi penyimpanan, dan biaya operasional untuk verifikasi integritas citra digital skala besar.
References
[1] A. R. S. Muhammad Bilal Fauzan, “Pengaruh Teknologi Visual Pengalaman Pengguna: Impilikasi Terhadap Budaya Konsumsi Dan Identitas Nasional,” Nov. 2024, doi: 10.5281/ZENODO.14167733.
[2] D. A. Lestari and F. Lubis, “Pengaruh Bukti Fotografi Dan Videografi Dalam Proses Pembuktian Perdata”.
[3] D. Maulana, N. S. Azzahrah, R. A. Syach, S. Syauri, M. Syafi’i, and C. Rozikin, “Identifikasi Konten Visual Buatan Ai Dengan Resnet Dan Fine-Grained Feature Extraction,” J. Inform. Dan Tek. Elektro Terap., vol. 13, no. 3S1, Oct. 2025, doi: 10.23960/jitet.v13i3S1.8056.
[4] J. C. Monge, “Dall-E 3 VS MidJourney 5.2 VS Stable XL — Same Prompt, Different Results,” Medium. Accessed: Apr. 25, 2026. [Online]. Available: https://generativeai.pub/dall-e-3-vs-midjourney-5-2-vs-stable-xl-same-prompt-different-results-a68ae19b223e
[5] E. P. Boediman, “Exploring the Impact of Deepfake Technology on Public Trust and Media Manipulation: A Scoping Review,” J. Komun., vol. 19, no. 2, pp. 313–334, Apr. 2025, doi: 10.20885/komunikasi.vol19.iss2.art8.
[6] A. Qureshi and D. Megías Jiménez, “Blockchain-Based Multimedia Content Protection: Review and Open Challenges,” Appl. Sci., vol. 11, no. 1, p. 1, Jan. 2021, doi: 10.3390/app11010001.
[7] S. A. R and J. Katiravan, “BlockImage: A Secure Framework for Image Authentication and Provenance Using AI and Blockchain,” J. Innov. Image Process., vol. 7, no. 1, pp. 28–49, Mar. 2025, doi: 10.36548/jiip.2025.1.002.
[8] Q. Hao, L. Luo, S. T. K. Jan, and G. Wang, “It’s Not What It Looks Like: Manipulating Perceptual Hashing Based Applications,” in Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event Republic of Korea: ACM, Nov. 2021, pp. 69–85. doi: 10.1145/3460120.3484559.
[9] C. Xiong, E. Liu, X. Li, H. Yao, L. Zhang, and C. Qin, “Perceptual Image Hashing Based on Multitask Neural Network,” Secur. Commun. Netw., vol. 2021, no. 1, p. 8297244, 2021, doi: 10.1155/2021/8297244.
[10] M. Hamadouche, K. Zebbiche, M. Guerroumi, H. Tebbi, and Y. Zafoune, “A Comparative Study of Perceptual Hashing Algorithms: Application on Fingerprint Images”.
[11] J. Madden, M. Bhavsar, L. Dorje, and X. Li, “Robustness of Practical Perceptual Hashing Algorithms to Hash-Evasion and Hash-Inversion Attacks,” Dec. 05, 2024, arXiv: arXiv:2406.00918. doi: 10.48550/arXiv.2406.00918.
[12] A. Hassan, “Perceptual Image Hashing by Exploiting a Visual Attention Model Along with Discrete Wavelet Transform and Discrete Cosine Transform,” J. Electron. Imaging, vol. 33, no. 6, p. 063057, Dec. 2024, doi: 10.1117/1.JEI.33.6.063057.
[13] C. Zauner, “Implementation and Benchmarking of Perceptual Image Hash Functions”.
[14] Q.-Y. Zhang, Z. Yang, Q.-Y. Dou, and Y. Yan, “Robust Hashing for Color Image Authentication Using Non-Subsampled Contourlet Transform Features and Salient Features”.
[15] V. Monga and B. L. Evans, “Perceptual Image Hashing Via Feature Points: Performance Evaluation and Tradeoffs,” IEEE Trans. Image Process., vol. 15, no. 11, pp. 3452–3465, Nov. 2006, doi: 10.1109/TIP.2006.881948.
[16] “(PDF) Robust Image Hashing Based on Structural and Perceptual Features for Authentication of Color Images,” ResearchGate, doi: 10.3906/elk-2002-6.
[17] A. Shahzad, W. Chen, Y. Zhang, and R. Kumar, “Zero-Trust Medical Image Sharing: A Secure and Decentralized Approach Using Blockchain and the IPFS,” Symmetry, vol. 17, no. 4, p. 551, Apr. 2025, doi: 10.3390/sym17040551.
[18] “Frontiers | Decentralizing video copyright protection: a novel blockchain-enabled framework with performance evaluation.” Accessed: Apr. 12, 2026. [Online]. Available: https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1655709/full
[19] Q. Hao, L. Luo, S. T. K. Jan, and G. Wang, “It’s Not What It Looks Like: Manipulating Perceptual Hashing based Applications,” in Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event Republic of Korea: ACM, Nov. 2021, pp. 69–85. doi: 10.1145/3460120.3484559.
[20] R. E. Arevalo-Ancona and M. Cedillo-Hernandez, “Zero-Watermarking for Medical Images Based on Regions of Interest Detection using K-Means Clustering and Discrete Fourier Transform,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 6, 2023, doi: 10.14569/IJACSA.2023.0140662.
[21] “Real vs AI faces Object Detection Dataset by Similarity,” Roboflow. Accessed: Apr. 20, 2026. [Online]. Available: https://universe.roboflow.com/similarity-rgq5n/real-vs-ai-faces-2vvfg
[22] “Portfolio (AI vs Real Images) Dataset > Overview,” Roboflow. Accessed: Apr. 20, 2026. [Online]. Available: https://universe.roboflow.com/similarity-rgq5n/portfolio-ai-vs-real-images-eitdu-nuqqb
[23] S. Nakamoto, “Bitcoin: A Peer-to-Peer Electronic Cash System”.
[24] D. G. Wood, “Ethereum: A Secure Decentralised Generalised Transaction Ledger”.
[25] T. S. Famuji, H. Herman, and S. Sunardi, “Smart Contract Penyimpanan Data Genetika Manusia Berbiaya Murah Pada Blockchain Ethereum,” J. Teknol. Inf. Dan Ilmu Komput., vol. 11, no. 3, pp. 695–704, Jul. 2024, doi: 10.25126/jtiik.1137558.
[26] T. Bicara, “Peran IPFS (InterPlanetary File System) Dalam Web3,” anakteknik.co.id. Accessed: Apr. 25, 2026. [Online]. Available: https://www.anakteknik.co.id/tatabicara12/articles/peran-ipfs-interplanetary-file-system-dalam-web3
[27] B. Chatwin, “Ethereum Gas Fees Explained.” Accessed: Apr. 25, 2026. [Online]. Available: https://www.dwellir.com/blog/ethereum-gas-fees-explained
[28] Coinvestasi, “coinvestasi,” Mengenal Arbitrum Proyek Layer-2 yang Curi Perhatian. Accessed: Apr. 25, 2026. [Online]. Available: https://coinvestasi.com/
[29] M. Kavitha, “Blockchain-Based Data Integrity Framework for Secure Cloud Storage Systems,” 2024.
[30] S. Srivastava, G. Kaur, Himank, and S. Singla, “Implementation of Blockchain and IPFS to Safeguard Evidentiary Data,” 2024 Int. Conf. Knowl. Eng. Commun. Syst. ICKECS, pp. 1–6, Apr. 2024, doi: 10.1109/ICKECS61492.2024.10616708.
[31] G. Sinaga, “Analisa Metode Imagehash Untuk Mendeteksi Orisinalitas Citra Digital,” vol. 1, no. 4, 2021.
