The field of financial security is witnessing significant advancements with the integration of machine learning techniques. Researchers are exploring innovative approaches to enhance the detection of money laundering and credit card fraud, such as the use of hybrid datasets, transformer-enhanced GAN oversampling, and deep learning methods. These techniques aim to improve the accuracy and effectiveness of financial security systems, addressing the challenges of class imbalance and data quality. Notably, the development of new algorithms and models, such as those utilizing centrality algorithms and autoregressive decision trees, is paving the way for more robust and efficient financial security solutions. Some noteworthy papers in this area include:

• A study on hybrid data for enhancing the utility of synthetic data for training anti-money laundering models, which demonstrates the potential of hybrid datasets in improving model utility while preserving privacy.
• A paper on oversampling and downsampling with core-boundary awareness, which proposes a data quality-driven approach to improve the effectiveness of machine learning models in unbalanced classification tasks.
• A work on TABFAIRGDT, a fast fair tabular data generator using autoregressive decision trees, which achieves a better fairness-utility trade-off for downstream tasks and higher synthetic data quality compared to state-of-the-art deep generative models.