Trustworthy Artificial Intelligence for Cyber Threat Analysis

TL;DR

This paper presents a machine learning-based cyber threat detection tool that combines unsupervised and supervised learning on cloud log data, demonstrating high-confidence threat identification and exploring quantum mechanics for speed improvements.

Contribution

It introduces a novel two-stage machine learning approach for cyber threat analysis on cloud data, integrating quantum mechanics for classification speed enhancement.

Findings

High-confidence threat detection achieved

Effective use of unsupervised and supervised learning

Potential speed improvements via quantum mechanics

Abstract

Artificial Intelligence brings innovations into the society. However, bias and unethical exist in many algorithms that make the applications less trustworthy. Threats hunting algorithms based on machine learning have shown great advantage over classical methods. Reinforcement learning models are getting more accurate for identifying not only signature-based but also behavior-based threats. Quantum mechanics brings a new dimension in improving classification speed with exponential advantage. In this research, we developed a machine learning based cyber threat detection and assessment tool. It uses two stage, unsupervised and supervised learning, analyzing method on log data recorded from a web server on AWS cloud. The results show the algorithm has the ability to identify cyber threats with high confidence.