Leveraging Finance AI and Machine Learning for APT Detection: Is Greater Precision Possible? (CASE STUDY)

EasyChair Preprint 14871

Abstract

Advanced Persistent Threats (APTs) represent a significant challenge in cybersecurity, characterized by their stealthy, prolonged nature and ability to bypass traditional security measures. This article explores the potential of machine learning algorithms to enhance the detection accuracy of APTs, an area of increasing interest given the rise of sophisticated cyber threats. By examining various machine learning techniques, including supervised and unsupervised learning, we aim to determine whether these methods can improve upon existing detection strategies. The study reviews the current landscape of APT detection, analyzing the strengths and weaknesses of conventional approaches, and how machine learning can address these gaps. Furthermore, the article evaluates the effectiveness of different machine learning models in real-world scenarios, focusing on their ability to identify APT patterns with greater precision and speed. The findings suggest that while machine learning holds promise for APT detection, achieving enhanced accuracy requires careful selection and optimization of algorithms.

Keyphrases: APT detection, Advanced Persistent Threats (APTs), Cybersecurity, Model Interpretability, Reinforcement Learning, anomaly detection, feature engineering, machine learning, supervised learning, unsupervised learning

@booklet{EasyChair:14871,
  author    = {Kayode Sheriffdeen},
  title     = {Leveraging Finance AI and Machine Learning for APT Detection: Is Greater Precision Possible? (CASE STUDY)},
  howpublished = {EasyChair Preprint 14871},
  year      = {EasyChair, 2024}}