Machine Learning and Cybersecurity

Abstract

The idea of quantum computers was developed by Richard Feynman and Yuri Manin. Quantum computation is a computational model which is based on the laws of quantum mechanics. Quantum computers can efficiently solve selected problems that are believed to be hard for classical machines. This is achieved by carefully exploiting quantum effects such as interference or likely entanglement. In the situation where the cyberattack are increasing in density and range, Quantum Computing companies, institutions and research groups may become targets of nation state actors, cybercriminals and hacktivists for sabotage, espionage and fiscal motivations. Quantum applications have expanded into commercial, classical information systems and services approaching the necessity to protect their networks, software, hardware and data from digital attacks. Recently, with the introduction of quantum computing, we have observed the introduction of quantum algorithms in Machine Learning. There are severalI. INTRODUCTION Networks have transformed our lives through many purposes such as email, file transfer, web search, e-commerce, online banking, monetary transaction, education, collaboration, social networking, etc. But we are disposed to serious security risks because the internet is an insecure mean of communication. Any device connected to the internet is vulnerable. Cybersecurity is safety against cyber-attacks. Cyber-attacks are launched by hackers to gain unauthorized access or steal important data. The estimated total damage caused by global cybercrime has increased from $300 billion in 2013 to $945 billion in 2020 (see [3, 4]). The Quantum computer Network is a network that connects distant quantum devices using quantum links in conjunction with conventional ones. Regular computers use and analyse data in bits (0 or 1), while quantum computers use qubits, or quantum bits, which can simultaneously represent other states aside from ones and zeros. This is the main difference between quantum computers and traditional computers. [2] The security of the internet will be seriously threatened by quantum computers. Many sectors, such as artificial intelligence, weather prediction, and medical research, carry significant potential for quantum computing. However, it also presents a serious risk to cyber security, suggesting us how to move in order to protect our data. Even though most of the present kinds of encryption can be decrypted by quantum computers, we still need to predict the threat and develop quantum-proof solutions. Furthermore, quantum technology will enhance cyber security. In today's cutting-edge technology, quantum devices can be utilized to enhance security by performing activities that are otherwise impossible, including secret key expansion with complete security [5]. Quantum machine learning (QML) can further improve the quality of conventional machine learning (ML) applications. These technologies in the noisy intermediate-scale quantum (NISQ) era explore the potential for developing systems that conclude with the search for advanced applications by quantum technologies. Modern ML has provided us with generative modeling techniques that are perfectly suited for the emerging landscape of NISQ hardware. An excellent example of this is the development of security systems against computer threats. There are three approaches of QML algorithms [7]: First, QML algorithms which are the quantum versions of conventional ML algorithms; second, the quantum-inspired ML algorithms that use the principles of quantum computing to improve classical methods of ML algorithms; third, the hybrid quantum-classical ML which combine quantum algorithms and classical ML algorithms to improve performance. [6]