ANN-Based Framework for Mitigation of Black Money Transactions in Crypto Exchange


  • Muzzamil Mustafa Lecturer, Department of Artificial Intelligence UMT Lahore
  • Muhammad Zulkifl Hasan Senior Lecturer, Faculty of CS University of Central Punjab Lahore
  • Saad Hussain Chuhan Student, Department of CS NCBA&E, Lahore
  • Muhammad Zunnurain Hussain Assistant Professor Baharia University Lahore Campus
  • Nadeem Sarwar Assistant Professor, Department of CS Baharia University Lahore Campus
  • Basit Sattar Lecturer, Department of AI University of Management & Technology Lahore


Cryptocurrencies have gained a lot of attention in the last 12 years after the launch of Bitcoin's decentralized system which allows direct online payments, Bitcoin opens up the way for many other digital currencies and coins like BNB, Ethereum, ETC (Ethereum Classic), XRP (Ripple), and many others. Many developed countries like America, Germany, France, and Belarus have started accepting payments from digital currency wallets, and their trade exchanges also allow trade through these digital coins and currencies, people of their countries use these currencies as digital financial assets, but many countries are even not ready to accept or legalize these digital currencies and coins due to chance of fraud, cyber security issues, anonymity, and privacy issues. In this paper, we have presented an ANN-based framework through which we can give a way to overcome these threats and vulnerabilities which will be helpful to countries who are looking to regularize it and who have security concerns over it. We have tested our dataset on two different models of Neural Networks, ANN and CNN. In the results CNN gives an accuracy of 81.97% on the other hand ANN gives the best accuracy of 96.72% on our dataset.




How to Cite

Mustafa, M., Hasan, M. Z., Chuhan, S. H., Hussain, M. Z., Sarwar, N., & Sattar, B. (2024). ANN-Based Framework for Mitigation of Black Money Transactions in Crypto Exchange. Journal of Computers and Intelligent Systems, 1(1). Retrieved from

Most read articles by the same author(s)