cryptanalysis and improvement of multimodal data encryption by machine-learning based system

Abstract

With the rising popularity of the internet and the widespread use of networks and information systems via the cloud and data centers, the privacy and security of individuals and organizations have become extremely crucial. In this perspective, encryption consolidates effective technologies that can effectively fulfill these requirements by protecting public information exchanges. To achieve these aims, the researchers used a wide assortment of encryption algorithms to accommodate the varied requirements of this field, as well as focusing on complex mathematical issues during their work to substantially complicate the encrypted communication mechanism. as much as possible to preserve personal information while significantly reducing the possibility of attacks. Depending on how complex and distinct the requirements established by these various applications are, the potential of trying to break them continues to occur, and systems for evaluating and verifying the cryptographic algorithms implemented continue to be necessary. The best approach to analyzing an encryption algorithm is to identify a practical and efficient technique to break it or to learn ways to detect and repair weak aspects in algorithms, which is known as cryptanalysis. Experts in cryptanalysis have discovered several methods for breaking the cipher, such as discovering a critical vulnerability in mathematical equations to derive the secret key or determining the plaintext from the ciphertext. There are various attacks against secure cryptographic algorithms in the literature, and the strategies and mathematical solutions widely employed empower cryptanalysts to demonstrate their findings, identify weaknesses, and diagnose maintenance failures in algorithms. The establishment of artificial intelligence models and approaches to provide a measure of the relative degree of protection for cryptographic systems represents one of the most recent strategies implemented in this field. This thesis research expanded on work through an automated testing strategy that comprises artificial intelligence methodologies to empower machine learning models to synthesize meaningful patterns and sensitive information from the ciphertext. Unlike classical cryptanalysis, the goal is to accomplish an automated and effective set of experiments without any human intervention. The added value of our contribution is to enrich the results of previous research which addresses the shortcomings by evaluating P-box permutation algorithms using deep learning. So that we investigate the benefits of deep learning cryptanalysis techniques in the evaluation process, using the features of convolutional neural network in black box attack to detect association between interchangeable entities in order to extract the plaintext effectively and efficiently from the ciphertext without any P-box knowledge. This thesis also deals with the study of the security of lightweight encryption used in the Internet of Things through the realization of several experiments and conclusions.