Employing Data Analytics For Identifying Potential Financial Frauds Through Adversarial Training On Imbalanced Datasets

Financial fraud is a major global issue, costing businesses and individuals billions of dollars annually. To combat this growing threat, organizations increasingly rely on machine learning models to detect fraudulent activities in financial transactions. However, a major obstacle in developing effective fraud detection systems is the imbalance in datasets, where genuine transactions vastly outnumber fraudulent ones. This data imbalance creates significant challenges for machine learning models, often leading to poor performance in identifying the very instances they are meant to detect. This has led to a new type of attack by users termed as adversarial machine learning in which the machine learning model used in the backend is targeted rather than the from end or the APIs. This is even more challenging due to imbalanced datasets. In conventional attacks, the first line of attack is the front end of the software. In this case, the machine learning model used in the backend is fed with bogus and/or deliberately falsified data to make it inactive. This is termed as adversarial machine learning attack or adversarial cyber-attack. It is extremely challenging to detect such attacks as there are no clear  signs of attacks such as redirections, malicious code scripts, auto refresh tags etc. Instead, the data fed to the back-end machine learning model is targeted using adversarial data feeds. In this paper, a deep learning based model is used to detect such attacks which attains lower MSE compared to existing work in the domain.