DEEP LEARNING-BASED CLASSIFICATION OF AUTHENTIC AND TAMPERED IMAGES WITH TAMPERING LOCALIZATION VIA IMAGE PROCESSING

Authors

  • Usman Khalid Faculty of Computer Science and Information Technology, The Superior University, Lahore, Pakistan,Department of Computer Science, The Superior University, Lahore, Pakistan Author
  • H. M. Shahzad Faculty of Computer Science and Information Technology, The Superior University, Lahore, Pakistan,Department of Software Engineering, The Superior University, Lahore, Pakistan Author
  • Munazzah Siddique Faculty of Computing, University of Okara, Pakistan, Department of Computer Science, University of Okara, Pakistan Author
  • Muhammad Asad Saqlain Faculty of Computer Science and Information Technology, The Superior University, Lahore, Pakistan, Department of Computer Science, The Superior University, Lahore, Pakistan Author

Keywords:

Deep learning Authentic images Tampered images Tamper localization Image forgery detection

DOI:

1102/3428

Abstract

Digital photographs underpin evidence in journalism, law, and
medicine, yet skillfully forged images can still evade casual
inspection. This paper introduces an InceptionV3-based network that
simultaneously classifies images as authentic or tampered, while
also identifying the manipulated regions. Experiments were
conducted on the CASIA v2.0 dataset, which contains 7,492
authentic and 5,123 tampered images with 5,123 corresponding
ground truth images. We use an 85% / 7.5% / 7.5% split for training,
validation, and testing. All images are resized to 224 x 224 px and
normalized to [0, 1] be-fore end-to-end training with Adam (initial
learning rate 1 x 10−4
) and categorical cross-entropy. The proposed
model attains 95.31% accuracy on the test set, surpassing recent
InceptionV3 baselines despite its compact architecture. Tamper
localization is achieved by thresholding the network’s dual-branch
saliency map, which is then overlaying binary ground-truth
contours. These overlays accurately highlight boundaries, even
under aggressive JPEG compression and minor edits. By sharing
features between detection and localization, the network learns
forensic artifacts blocking, boundary mismatches, and illumination
discontinuities, without the need for auxiliary loss terms or attention
modules. Code, trained weights, and evaluation scripts are made
publicly available to ensure full reproducibility.

Downloads

Published

2026-10-16