Information Security Based on LLM Approaches: A Review

TL;DR

This review addresses the growing challenges in information security and assesses how large language models and Transformer-based architectures can enhance protective capabilities. It surveys applications across malware detection, network threat analysis, vulnerability discovery, and cryptographic considerations, highlighting improvements in detection accuracy and reductions in false alarms. The study also identifies critical challenges such as model transparency, interpretability, and cross-domain adaptability, and outlines directions for future work including robust defenses against adversarial inputs, automated threat intelligence collection, and extended cryptographic use-cases. Overall, the work provides theoretical and practical guidance for deploying LLM-based solutions to create more intelligent and proactive security systems.

Abstract

Information security is facing increasingly severe challenges, and traditional protection means are difficult to cope with complex and changing threats. In recent years, as an emerging intelligent technology, large language models (LLMs) have shown a broad application prospect in the field of information security. In this paper, we focus on the key role of LLM in information security, systematically review its application progress in malicious behavior prediction, network threat analysis, system vulnerability detection, malicious code identification, and cryptographic algorithm optimization, and explore its potential in enhancing security protection performance. Based on neural networks and Transformer architecture, this paper analyzes the technical basis of large language models and their advantages in natural language processing tasks. It is shown that the introduction of large language modeling helps to improve the detection accuracy and reduce the false alarm rate of security systems. Finally, this paper summarizes the current application results and points out that it still faces challenges in model transparency, interpretability, and scene adaptability, among other issues. It is necessary to explore further the optimization of the model structure and the improvement of the generalization ability to realize a more intelligent and accurate information security protection system.

Figures (9)

• Figure 1: Neural Network Structure Diagram
• Figure 2: Reinforcement Learning Structure Diagram
• Figure 3: Transformer Overall Architecture Diagram
• Figure 4: Modern Cryptography
• Figure 5: Binary to Malware Image