Contextualized AI for Cyber Defense: An Automated Survey using LLMs

TL;DR

This paper explores how contextualized AI, especially large language models, can enhance cyber defense by analyzing recent research trends, methodologies, and challenges, offering insights for future development and trust-building in AI-driven security.

Contribution

It introduces a novel LLM-assisted survey methodology to analyze research on AI in cyber defense, highlighting current focus areas and identifying gaps in trust and governance.

Findings

Research on AI in cyber defense has grown significantly from 2015 to 2024.

LLM-assisted survey methods are effective for literature exploration and filtering.

Challenges include trust, reliability, and governance in deploying AI for security.

Abstract

This paper surveys the potential of contextualized AI in enhancing cyber defense capabilities, revealing significant research growth from 2015 to 2024. We identify a focus on robustness, reliability, and integration methods, while noting gaps in organizational trust and governance frameworks. Our study employs two LLM-assisted literature survey methodologies: (A) ChatGPT 4 for exploration, and (B) Gemma 2:9b for filtering with Claude 3.5 Sonnet for full-text analysis. We discuss the effectiveness and challenges of using LLMs in academic research, providing insights for future researchers.