Umělá inteligence v šifrování

This thesis focuses on the application of artificial intelligence (AI) in the field of cryptography. Large Language Models (LLM) such as ChatGPT, Perplexity, and Claude make the use of neural networks easier than ever before. This brings enormous potential for application and use by ordinary users in various areas of life, including cryptography. The aim of this work is to analyse the potential use of LLM in the areas of encoding, cryptanalysis, and creation of cryptographic algorithms. The thesis is divided into seven chapters, four of which are theoretical. The first chapter provides a basic overview of the field of cryptography. The second chapter discusses the issue of encoding, which is an integral part of cryptographic processes. The third chapter is devoted to the topic of artificial intelligence, while the fourth chapter follows with a focus on LLM. The practical part consists of three chapters. The fifth chapter explores the possibilities of LLM for encoding. This is followed by the sixth chapter on cryptanalysis for simple ciphers. In the seventh chapter, the thesis examines the possibilities of cryptographic algorithms using LLM. The conclusion summarizes the main results of the work, the future direction of the field, and the limitations associated with LLM.