Download PDFOpen PDF in browser

AI and Machine Learning for Advanced Persistent Threat Detection in Finance: Towards Higher Accuracy and Better Protection

EasyChair Preprint 14635

10 pagesDate: August 31, 2024

Abstract

In the finance sector, Advanced Persistent Threats (APTs) pose significant cybersecurity risks due to their stealthy and sophisticated nature. Traditional detection methods often struggle to identify these evolving threats, necessitating more advanced solutions. This article explores the potential of Artificial Intelligence (AI) and Machine Learning (ML) in enhancing APT detection accuracy within financial institutions. By leveraging AI and ML, financial entities can automate threat detection, reduce false positives, and continuously learn from new attack patterns, providing a more dynamic and robust defense against cyber threats. However, implementing these technologies also presents challenges, including data quality, model interpretability, and vulnerability to adversarial attacks. This article discusses the integration of AI and ML with traditional cybersecurity measures, the importance of explainable AI, and the need for interdisciplinary approaches to strengthen APT detection. By examining current trends, challenges, and future directions, this study provides insights into how financial institutions can achieve superior accuracy in detecting and mitigating APTs through AI and ML advancements.

Keyphrases: Advanced Persistent Threats (APTs), Artificial Intelligence (AI), Cybersecurity, Explainable AI, Financial Sector, Machine Learning (ML), Threat Detection, adversarial attacks, anomaly detection, data privacy

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:14635,
  author    = {Alakitan Samad},
  title     = {AI and Machine Learning for Advanced Persistent Threat Detection in Finance: Towards Higher Accuracy and Better Protection},
  howpublished = {EasyChair Preprint 14635},
  year      = {EasyChair, 2024}}
Download PDFOpen PDF in browser