• Home
  • Search
  • Source camera attribution using a rule-based explainable convolutional neural network
  • https://doi.org/10.1038/s41598-026-40387-9Copy DOI Icon

Source camera attribution using a rule-based explainable convolutional neural network

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

In recent years, there has been a push towards adopting artificial intelligence (AI) models in digital forensics (DF), particularly deep learning (DL) models. While these models assist DF experts, their lack of transparency raises concerns about reliability. Although eXplainable Artificial Intelligence (XAI) has progressed, current methods remain limited for DF applications. Existing visual XAI techniques do not provide sufficient clarity for challenging image forensics tasks such as Source Camera Identification (SCI), nor do they offer mechanisms to assess whether a model’s decision is correct. Most methods simply highlight influential regions without enabling examiners to validate the decision itself. Rule-based explainability is a promising strategy for increasing transparency, yet deploying it on real-world Convolutional Neural Networks (CNNs) is still challenging. Prior studies remain largely experimental and often require modifying the model to extract rules, conflicting with the integrity requirements of DF workflows. To address these gaps, this paper introduces a framework to make CNN models used in the analysis stage of digital forensics explainable. The framework, by following three fundamental steps—layers trace detection, layers majority voting, and rule extraction—provides structured and transparent visual output, and rule-based textual explainability that is understandable to the user. Based on this, the first explainable Source Camera Identification (SCI) model is introduced which is a challenging DF task to make it explainable. The explainable output allows for the rejection or confirmation of the main model’s prediction based on the decisions of the layers and compliance with the principle of integrity to the DF examiner. In addition, with the identification of 27 out of 37 incorrect predictions by the base model, the precision of the model was improved from 97.33% to 99.2%.

Similar Papers
  • Research Article

A Comprehensive Review of Deepfake Detection Pertaining to Images, Videos, Audio, and News using Deep Learning Techniques

  • Apr 30, 2025
  • Engineering and Technology Journal
  • Vakdevi Vallabhaneni +7
  • Research Article
  • Citations7

Artificial Intelligence: The Future of Maxillofacial Prognosis and Diagnosis?

  • Feb 26, 2021
  • Journal of Oral and Maxillofacial Surgery
  • Peter Rekawek +2
  • Research Article
  • Citations1

AI And Deep Learning Models for Early Lung Cancer Detection Using Radiological Data

  • Jan 31, 2025
  • Journal of Informatics Education and Research
  • K Anusheebha, Blessed Prince P
  • Research Article
  • Citations10

AI-Driven Predictive Maintenance for Energy Infrastructure

  • Jan 01, 2024
  • International Journal of Research and Scientific Innovation
  • Ibrahim Adeiza Ahmed +1
  • Book Chapter
  • Citations5

Universal Wavelet Relative Distortion: A New Counter–Forensic Attack on Photo Response Non-Uniformity Based Source Camera Identification

  • Jan 01, 2018
  • Venkata Udaya Sameer +1
  • Research Article
  • Citations16

The challenges and opportunities of adopting artificial intelligence (AI) in Jordan’s healthcare transformation

  • Oct 31, 2021
  • Global Journal of Information Technology: Emerging Technologies
  • Shakir Karim +2
  • Research Article

A Review of Artificial Intelligence-Assisted Diagnostic Imaging Tools in the Detection and Characterization of Brain Tumors

  • Aug 15, 2025
  • Peta International Journal of Public Health
  • Wu Dongping* +2
  • Discussion
  • Citations1

Detection of metastasis of mediastinal lymph nodes in lung cancer patients with an artificial intelligence model.

  • May 05, 2023
  • Chinese Medical Journal
  • Xiao Sun +8
  • Research Article
  • Citations4

Generalizing Source Camera Identification Based on Integral Image Optimization and Constrained Neural Network

  • Sep 12, 2024
  • Electronics
  • Yan Wang +2
  • PDF
  • Research Article
  • Citations3

Diagnostic accuracy of AI or DL-enhanced technologies in the diagnosis of diabetic retinopathy: a systematic review

  • Nov 06, 2025
  • Journal of Medical Imaging and Interventional Radiology
  • Reem Dhobaian Alshammari +2
  • Research Article
  • Citations375

Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study

  • May 01, 2019
  • The Lancet Digital Health
  • Valentina Bellemo +19
  • Research Article
  • Citations10

Machine learning and clinical EEG data for multiple sclerosis: A systematic review.

  • Aug 01, 2025
  • Artificial intelligence in medicine
  • Badr Mouazen +3
  • Research Article
  • Citations10

Real-World Surveillance of FDA-Cleared Artificial Intelligence Models: Rationale and Logistics.

  • Feb 01, 2022
  • Journal of the American College of Radiology
  • Keith J Dreyer +2
  • PDF
  • Research Article
  • Citations10

Identifying Financial Market Trend Reversal Behavior With Structures of Price Activities Based on Deep Learning Methods

  • Jan 01, 2022
  • IEEE Access
  • Chern-Bin Ju +1
  • PDF
  • Research Article
  • Citations19

A hybrid CNN and ensemble model for COVID-19 lung infection detection on chest CT scans.

  • Mar 09, 2023
  • PLOS ONE
  • Ahmed A Akl +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.