Knowledge-Enhanced Neurosymbolic Artificial Intelligence for Cybersecurity and Privacy

Thumbnail Image

Files

2308.02031.pdf (791.7 KB)

Links to Files

https://ieeexplore.ieee.org/abstract/document/10266743

Permanent Link

https://doi.org/10.1109/MIC.2023.3299435
 http://hdl.handle.net/11603/30224

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection

Author/Creator

Author/Creator ORCID

https://orcid.org/0009-0006-6081-9896
 https://orcid.org/0000-0002-5411-2230
 https://orcid.org/0000-0002-8641-3193

Date

2023-09-28

Type of Work

journal articles
preprints
Text

Department

Program

Citation of Original Publication

Piplai, Aritran, Anantaa Kotal, Seyedreza Mohseni, Manas Gaur, Sudip Mittal, and Anupam Joshi. “Knowledge-Enhanced Neurosymbolic Artificial Intelligence for Cybersecurity and Privacy.” IEEE Internet Computing 27, no. 5 (September 2023): 43–48. https://doi.org/10.1109/MIC.2023.3299435.

Rights

© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Subjects

Abstract

Neurosymbolic artificial intelligence (AI) is an emerging and quickly advancing field that combines the subsymbolic strengths of (deep) neural networks and the explicit, symbolic knowledge contained in knowledge graphs (KGs) 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 unknown unknowns (e.g., cybersecurity, privacy). The integration of neural networks, which excel at exploring complex data spaces, and symbolic KGs, 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 of the most demanding domains in terms of the need for AI to be explainable while being highly accurate in complex environments, can benefit from neurosymbolic AI.