Note: This video may require joining the NVIDIA Developer Program or login

GTC Silicon Valley-2019 ID:S9361:Creation of Adversarial Accounting Records to Attack Financial Statement Audits

Timur Sattarov(PricewaterhouseCoopers GmbH WPG),Marco Schreyer(German Research Center for Artificial Intelligence)
We'll explore how auditors can be misguided or fooled by adversarial accounting records or adversarial financial transactions. Recent discoveries in deep learning research revealed that learned models are vulnerable to adversarial examples, or a sample of slightly modified input data that intends to cause a human and/or machine to misclassify it. Such examples exhibit the potential to be dangerous because they could be specifically designed to misguide auditors or an accountant. Securing accounting information systems against such attacks can be difficult.

View the slides (pdf)