Integrating Generative AI into Cybersecurity Education: A Study of OCR and Multimodal LLM-assisted Instruction

2025-09-03

AI Summary

Addressing the dual challenges of skill gaps among older learners and platform compatibility limitations under Industry 4.0, this paper proposes a lightweight zero-shot OCR-LLM pedagogical assistance framework for cybersecurity education. It leverages Tesseract OCR to extract textual content from instructional materials and integrates off-the-shelf large language models (LLMs) to generate simplified, step-by-step operational instructions—seamlessly embedded into a virtual cybersecurity laboratory platform. By avoiding computationally intensive multimodal LLMs and operating exclusively on extracted text, the framework achieves near-equivalent performance with significantly reduced deployment costs. Empirical evaluation in university courses yielded an average student satisfaction score of 7.83/10, confirming its pedagogical utility and intergenerational accessibility. The core contribution is the first application of a zero-shot OCR-LLM pipeline to cybersecurity education, uniquely balancing accessibility, computational efficiency, and instructional effectiveness.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Security and Privacy: Large-scale security measurements

Abstract

This full paper describes an LLM-assisted instruction integrated with a virtual cybersecurity lab platform. The digital transformation of Fourth Industrial Revolution (4IR) systems is reshaping workforce needs, widening skill gaps, especially among older workers. With rising emphasis on robotics, automation, AI, and security, re-skilling and up-skilling are essential. Generative AI can help build this workforce by acting as an instructional assistant to support skill acquisition during experiential learning. We present a generative AI instructional assistant integrated into a prior experiential learning platform. The assistant employs a zero-shot OCR-LLM pipeline within the legacy Cybersecurity Labs-as-a-Service (CLaaS) platform (2015). Text is extracted from slide images using Tesseract OCR, then simplified instructions are generated via a general-purpose LLM, enabling real-time instructional support with minimal infrastructure. The system was evaluated in a live university course where student feedback (n=42) averaged 7.83/10, indicating strong perceived usefulness. A comparative study with multimodal LLMs that directly interpret slide images showed higher performance on visually dense slides, but the OCR-LLM pipeline provided comparable pedagogical value on text-centric slides with much lower computational overhead and cost. This work demonstrates that a lightweight, easily integrable pipeline can effectively extend legacy platforms with modern generative AI, offering scalable enhancements for student comprehension in technical education.

Problem

• Integrating generative AI into cybersecurity education platforms
• Addressing workforce skill gaps through AI-assisted experiential learning
• Providing real-time instructional support with minimal computational overhead

Innovation

• OCR-LLM pipeline for instructional support
• Zero-shot text extraction with Tesseract OCR
• Lightweight integration with legacy CLaaS platform