# Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks

arXiv: https://arxiv.org/abs/1908.00734 · HTML: https://mlsanity.com/paper/1908.00734/

## Key facts

- Cited by 13 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 2 Aug 2019.

## Built on by (most cited first, 13 of 13)

- [Multi-view Contrastive Self-Supervised Learning of Accounting Data Representations for Downstream Audit Tasks](https://mlsanity.com/paper/2109.11201/) (2021)
- [Machine Learning in NextG Networks via Generative Adversarial Networks](https://mlsanity.com/paper/2203.04453/) (2022)
- [Federated and Privacy-Preserving Learning of Accounting Data in Financial Statement Audits](https://mlsanity.com/paper/2208.12708/) (2022)
- [Explaining Anomalies using Denoising Autoencoders for Financial Tabular Data](https://mlsanity.com/paper/2209.10658/) (2022)
- [Federated Continual Learning to Detect Accounting Anomalies in Financial Auditing](https://mlsanity.com/paper/2210.15051/) (2022)
- [Anomaly Detection in Double-entry Bookkeeping Data by Federated Learning System with Non-model Sharing Approach](https://mlsanity.com/paper/2501.12723/) (2025)
- [Fin-Fed-OD: Federated Outlier Detection on Financial Tabular Data](https://mlsanity.com/paper/2404.14933/) (2024)
- [Advancing Anomaly Detection: Non-Semantic Financial Data Encoding with LLMs](https://mlsanity.com/paper/2406.03614/) (2024)
- [Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data](https://mlsanity.com/paper/2508.00758/) (2025)
- [RESHAPE: Explaining Accounting Anomalies in Financial Statement Audits by enhancing SHapley Additive exPlanations](https://mlsanity.com/paper/2209.09157/) (2022)
- [A Combination of Deep Neural Networks and K-Nearest Neighbors for Credit Card Fraud Detection](https://mlsanity.com/paper/2205.15300/) (2022)
- [Open ERP System Data For Occupational Fraud Detection](https://mlsanity.com/paper/2206.04460/) (2022)
- [Anomaly Detection in General Ledger Data: Results from a Hybrid Approach](https://mlsanity.com/paper/2609.18228/) (2026)

## Abstract (arXiv)

The detection of fraud in accounting data is a long-standing challenge in financial statement audits. Nowadays, the majority of applied techniques refer to handcrafted rules derived from known fraud scenarios. While fairly successful, these rules exhibit the drawback that they often fail to generalize beyond known fraud scenarios and fraudsters gradually find ways to circumvent them. In contrast, more advanced approaches inspired by the recent success of deep learning often lack seamless interpretability of the detected results. To overcome this challenge, we propose the application of adversarial autoencoder networks. We demonstrate that such artificial neural networks are capable of learning a semantic meaningful representation of real-world journal entries. The learned representation provides a holistic view on a given set of journal entries and significantly improves the interpretability of detected accounting anomalies. We show that such a representation combined with the networks reconstruction error can be utilized as an unsupervised and highly adaptive anomaly assessment. Experiments on two datasets and initial feedback received by forensic accountants underpinned the effectiveness of the approach.