A PROOF OF CONCEPT FOR ML-DRIVEN PAYMENT CARD INDUSTRY DATA SECURITY STANDARD (PCI DSS) AUDIT SYSTEMS

Date

2025-6-25

Author

AVCI, ZEYNEL ABIDIN

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

117
views

19
downloads

Cite This

Today, PCI DSS audits are mostly manual, which takes a lot of time and is often prone to mistakes. Problems like slow evidence collection, inconsistent policy reviews, and late threat detection can leave gaps in compliance and raise security risks. By using machine learning, we can automate key steps like gathering evidence, reviewing policies, and spotting threats in real time. This reduces the need for manual work and makes the process more accurate. The proposed system uses machine learning continuous monitoring and predicts where problems might arise, so organizations can fix issues before they become serious. This not only makes audits smoother but also matches the latest PCI DSS standards, which focus on ongoing monitoring and flexible security. Our project presents a proof of concept for a machine learning-based PCI DSS audit system that tackles these challenges and helps improve compliance management.

Subject Keywords

PCI DSS, Machine Learning, Continuous Monitoring, Adaptive Security, Compliance Management, Suptech

URI

https://hdl.handle.net/11511/115074

Collections

Graduate School of Informatics, Term Project