Knowledge-enhanced Neuro-Symbolic AI for Cybersecurity and Privacy

TL;DR

This paper discusses how Neuro-Symbolic AI combines neural networks and symbolic knowledge graphs to improve explainability and safety in cybersecurity and privacy applications.

Contribution

It introduces a framework leveraging Neuro-Symbolic AI to enhance reasoning, learning, and generalization in cybersecurity and privacy domains.

Findings

Improved explainability of AI decisions in cybersecurity.

Enhanced safety and handling of unknown scenarios.

Better integration of domain knowledge into AI systems.

Abstract

Neuro-Symbolic Artificial Intelligence (AI) is an emerging and quickly advancing field that combines the subsymbolic strengths of (deep) neural networks and explicit, symbolic knowledge contained in knowledge graphs to enhance explainability and safety in AI systems. This approach addresses a key criticism of current generation systems, namely their inability to generate human-understandable explanations for their outcomes and ensure safe behaviors, especially in scenarios with \textit{unknown unknowns} (e.g. cybersecurity, privacy). The integration of neural networks, which excel at exploring complex data spaces, and symbolic knowledge graphs, which represent domain knowledge, allows AI systems to reason, learn, and generalize in a manner understandable to experts. This article describes how applications in cybersecurity and privacy, two most demanding domains in terms of the need for AI to be explainable while being highly accurate in complex environments, can benefit from Neuro-Symbolic AI.