Signal Knowledge Graph

TL;DR

This paper introduces a specialized knowledge graph designed to improve reasoning over signals from multiple sources for intelligence analysis, addressing limitations of existing systems by modeling attacker behavior and signal context.

Contribution

It proposes a novel knowledge graph framework that incorporates attacker behavior, signal emission, and receiver characteristics for enhanced signal reasoning in intelligence applications.

Findings

Addresses limitations of existing knowledge graphs for signal reasoning

Models attacker behavior and signal context explicitly

Improves inference accuracy over combined signal data

Abstract

This paper presents an knowledge graph to assist in reasoning over signals for intelligence purposes. We highlight limitations of existing knowledge graphs and reasoning systems for this purpose, using inference of an attack using combined data from microphones, cameras and social media as an example. Rather than acting directly on the received signal, our approach considers attacker behaviour, signal emission, receiver characteristics, and how signals are summarised to support inferring the underlying cause of the signal.