EXIF Metadata Feature Extraction to Improve Source Device Identification Accuracy in Digital Images within a Digital Forensics Approach

Muhammad Naufal Bahreisy, Adi Rizky Pratama, Gugy Guztaman Munzi, Yusuf Eka Wicaksana

Abstract


This study aims to develop and evaluate methods for digital image source device identification through three main approaches, namely EXIF metadata feature extraction, visual analysis using Convolutional Neural Networks (CNN), and Photo Response Non-Uniformity (PRNU). The dataset consists of 500 original images captured from five different devices, with 100 images per device containing intact metadata. The EXIF-only model was built using the Random Forest algorithm, the CNN model employed a ResNet18 architecture, while PRNU utilized high-pass filtering to construct sensor noise templates for each device. Evaluation was carried out using accuracy, precision, recall, and f1-score metrics. The results show that EXIF-only achieved perfect accuracy (100%) on the dataset with complete metadata, CNN reached 21% accuracy with imbalanced recall across classes, and PRNU demonstrated low performance due to the limited number of templates and image quality. These findings indicate that EXIF-only excels under intact metadata conditions but is vulnerable to manipulation, CNN can be applied when metadata is unavailable but requires optimization, while PRNU has potential resilience against metadata manipulation but demands higher-quality data. The novelty of this study lies in its comparative multi-method approach that integrates metadata-based, visual-based, and sensor fingerprint-based analyses, along with the proposal of a multimodal integration framework to enhance the reliability of device identification systems in digital forensic practice.

Keywords


Digital Forensics; Convolutional Neural Network; PRNU; Image Forensics

Full Text:

PDF

References


D. Cozzolino and L. Verdoliva, “Noiseprint: A CNN-Based Camera Model Fingerprint,” Ieee Trans. Inf. Forensics Secur., vol. 15, pp. 144–159, 2020, doi: 10.1109/tifs.2019.2916364.

Z. Balkibayeva, “Methods of Extracting and Analyzing Metadata for Evidentiary Purposes,” Uzb. J. Law Digi. Policy, vol. 2, no. 5, pp. 31–44, 2024, doi: 10.59022/ujldp.233.

D. Cozzolino, F. Marra, D. Gragnaniello, G. Poggi, and L. Verdoliva, “Combining PRNU and Noiseprint for Robust and Efficient Device Source Identification,” Eurasip J. Inf. Secur., vol. 2020, no. 1, 2020, doi: 10.1186/s13635-020-0101-7.

F. A. Musyaffa, K. Rapp, and H. Gohlke, “LISTER: Semiautomatic Metadata Extraction From Annotated Experiment Documentation in eLabFTW,” J. Chem. Inf. Model., vol. 63, no. 20, pp. 6224–6238, 2023, doi: 10.1021/acs.jcim.3c00744.

M. Manisha, C. Li, and A. K. Karunakar, “Source Camera Identification With a Robust Device Fingerprint: Evolution From Image-Based to Video-Based Approaches,” Sensors, vol. 23, no. 17, p. 7385, 2023, doi: 10.3390/s23177385.

J. Zeng and X. Qiu, “Forensic Taken Time Authentication of Mobile Phone Photos,” p. 17, 2024, doi: 10.1117/12.3048368.

Y. Wang, Q. Sun, D. Rong, S. Li, and L. D. Xu, “Image Source Identification Using Convolutional Neural Networks in IoT Environment,” Wirel. Commun. Mob. Comput., vol. 2021, no. 1, 2021, doi: 10.1155/2021/5804665.

O. Mayer and M. C. Stamm, “Forensic Similarity for Digital Images,” Ieee Trans. Inf. Forensics Secur., vol. 15, pp. 1331–1346, 2020, doi: 10.1109/tifs.2019.2924552.

M. Iuliani, M. Fontani, and A. Piva, “A Leak in PRNU Based Source Identification—Questioning Fingerprint Uniqueness,” Ieee Access, vol. 9, pp. 52455–52463, 2021, doi: 10.1109/access.2021.3070478.

M. Manisha, C. Li, X. Lin, and A. K. Karunakar, “Beyond PRNU: Learning Robust Device-Specific Fingerprint for Source Camera Identification,” Sensors, vol. 22, no. 20, p. 7871, 2022, doi: 10.3390/s22207871.

T. Zhao, X. Xu, M. Xu, H. Ding, Y. Xiong, and W. Xia, “Learning Self-Consistency for Deepfake Detection,” pp. 15003–15013, 2021, doi: 10.1109/iccv48922.2021.01475.

I. C. Camacho and K. Wang, “A Comprehensive Review of Deep-Learning-Based Methods for Image Forensics,” J. Imaging, vol. 7, no. 4, p. 69, 2021, doi: 10.3390/jimaging7040069.

X. Lin and C. Li, “PRNU-Based Content Forgery Localization Augmented With Image Segmentation,” Ieee Access, vol. 8, pp. 222645–222659, 2020, doi: 10.1109/access.2020.3042780.

C. Zeng, D. Zhu, Z. Wang, Z. Wang, N. Zhao, and L. He, “An End-to-End Deep Source Recording Device Identification System for Web Media Forensics,” Int. J. Web Inf. Syst., vol. 16, no. 4, pp. 413–425, 2020, doi: 10.1108/ijwis-06-2020-0038.

Y. Liu, Z. Zou, Y. Yang, N.-F. Law, and A. A. Bharath, “Efficient Source Camera Identification With Diversity-Enhanced Patch Selection and Deep Residual Prediction,” Sensors, vol. 21, no. 14, p. 4701, 2021, doi: 10.3390/s21144701.

A. Stolbova, A. Malyshev, and O. Golovnin, “Two-Step Intelligent Approach for Photo Image Fragment Forgery Detection and Identification,” p. 10, 2023, doi: 10.1117/12.2669232.

S. Agrawal, P. Kumar, S. Seth, T. Parag, M. Singh, and V. Babu, “SISL:Self-Supervised Image Signature Learning for Splicing Detection and Localization,” 2022, doi: 10.48550/arxiv.2203.07824.

K. A. Nfor, T. P. T. Armand, and H. Kim, “A Holistic Approach to Image Forensics: Integrating Image Metadata Analysis and ELA With CNN and MLP for Image Forgery.,” 2024, doi: 10.21203/rs.3.rs-4667372/v1.

S. Ferreira, M. Antunes, and M. E. Correia, “A Dataset of Photos and Videos for Digital Forensics Analysis Using Machine Learning Processing,” Data, vol. 6, no. 8, p. 87, 2021, doi: 10.3390/data6080087.




DOI: http://dx.doi.org/10.38101/sisfotek.v15i2.15998

Refbacks

  • There are currently no refbacks.


 

JURNAL SISFOTEK GLOBAL

Organized by: Research Center and Community Development
Published by: Institut Teknologi dan Bisnis Bina Sarana Global
Jl. Aria Santika No.43A, Margasari, Kec. Karawaci, Kota Tangerang, Banten 15114
Phone. +62 552 2727
Email: lppm@global.ac.id

INDEXED BY:

   


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License..
Based on a work at https://journal.global.ac.id/index.php/sisfotek/index.