Counterfeit Currency Detection Through Deep Convolutional Generative Adversarial Network

Worldwide, individuals, businesses, and economies are being affected by counterfeit currency significantly. Numerous models generate content that mimics the original, and existing solutions fall short in detecting the difference between real and fake. This study presents a detection system using three deep learning models: Deep Convolutional Generative Adversarial Network (DCGAN), Convolutional Neural Network (CNN), and Fully Connected Neural Network (FCNN). The proposed study also identifies patterns that contribute to real and fake currency when the models are trained on the data. After training the models, the proposed solution receives an accuracy of 95 per cent, an F1 Score of 0.957, 0.95 as precision, and 0.954 as recall. This study further carries out a comprehensive analysis of existing models and compares them with the proposed solution to determine the effectiveness of the solution and further recommend its implementation in real-world applications. The proposed solution contributes to the widespread adoption of the application across smart devices and further ensures a robust solution for the detection of counterfeit money.

@article{Jan2026,
  title     = {Counterfeit Currency Detection Through Deep Convolutional Generative Adversarial Network},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {7},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Salman Jan and Fara Gul and Mohammad Riyaz Belgaum and Shahid Kamal and Afaq Ahmad and Muhammad Bilal and Atif Khan},
  doi       = {10.14569/IJACSA.2026.0170735},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170735}
}