Adversarial Learning of Deepfakes in Accounting
This addresses a security vulnerability in financial auditing systems, which is an incremental application of existing adversarial attack methods to a new domain.
The paper tackles the problem of adversarial attacks on Computer Assisted Audit Techniques (CAATs) in accounting by introducing a threat model to camouflage fraudulent journal entries and demonstrating that adversarial autoencoder neural networks can generate robust adversarial entries that mislead these systems.
Nowadays, organizations collect vast quantities of accounting relevant transactions, referred to as 'journal entries', in 'Enterprise Resource Planning' (ERP) systems. The aggregation of those entries ultimately defines an organization's financial statement. To detect potential misstatements and fraud, international audit standards demand auditors to directly assess journal entries using 'Computer Assisted AuditTechniques' (CAATs). At the same time, discoveries in deep learning research revealed that machine learning models are vulnerable to 'adversarial attacks'. It also became evident that such attack techniques can be misused to generate 'Deepfakes' designed to directly attack the perception of humans by creating convincingly altered media content. The research of such developments and their potential impact on the finance and accounting domain is still in its early stage. We believe that it is of vital relevance to investigate how such techniques could be maliciously misused in this sphere. In this work, we show an adversarial attack against CAATs using deep neural networks. We first introduce a real-world 'thread model' designed to camouflage accounting anomalies such as fraudulent journal entries. Second, we show that adversarial autoencoder neural networks are capable of learning a human interpretable model of journal entries that disentangles the entries latent generative factors. Finally, we demonstrate how such a model can be maliciously misused by a perpetrator to generate robust 'adversarial' journal entries that mislead CAATs.