# Dual-Branch Convolutional Framework for Spatial and Frequency-Based Image Forgery Detection

arXiv: https://arxiv.org/abs/2509.05281 · HTML: https://mlsanity.com/paper/2509.05281/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [Noiseprint: a CNN-based camera model fingerprint](https://mlsanity.com/paper/1808.08396/) (2018)
- [On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection](https://mlsanity.com/paper/2410.23623/) (2024)
- [TransForensics: Image Forgery Localization with Dense Self-Attention](https://mlsanity.com/paper/2108.03871/) (2021)
- [A Timely Survey on Vision Transformer for Deepfake Detection](https://mlsanity.com/paper/2405.08463/) (2024)
- [Multi-Scale Wavelet Transformer for Face Forgery Detection](https://mlsanity.com/paper/2210.03899/) (2022)
- [Analysis of adversarial attacks against CNN-based image forgery detectors](https://mlsanity.com/paper/1808.08426/) (2018)
- [Trinity Detector:text-assisted and attention mechanisms based spectral fusion for diffusion generation image detection](https://mlsanity.com/paper/2404.17254/) (2024)
- [Digital Image Tamper Detection Techniques - A Comprehensive Study](https://mlsanity.com/paper/1306.6737/) (2013)
- [Detection of copy-move forgery in digital images based on DCT](https://mlsanity.com/paper/1308.5661/) (2013)
- [Rethinking Image Sensor Noise for Forensic Advantage](https://mlsanity.com/paper/1808.07971/) (2018)

## Abstract (arXiv)

With a very rapid increase in deepfakes and digital image forgeries, ensuring the authenticity of images is becoming increasingly challenging. This report introduces a forgery detection framework that combines spatial and frequency-based features for detecting forgeries. We propose a dual branch convolution neural network that operates on features extracted from spatial and frequency domains. Features from both branches are fused and compared within a Siamese network, yielding 64 dimensional embeddings for classification. When benchmarked on CASIA 2.0 dataset, our method achieves an accuracy of 77.9%, outperforming traditional statistical methods. Despite its relatively weaker performance compared to larger, more complex forgery detection pipelines, our approach balances computational complexity and detection reliability, making it ready for practical deployment. It provides a strong methodology for forensic scrutiny of digital images. In a broader sense, it advances the state of the art in visual forensics, addressing an urgent requirement in media verification, law enforcement and digital content reliability.