Opis tego kierunku w języku polskim znajdziesz tu>>
Gain an in-depth understanding of artificial intelligence concepts, principles and technologies that affect cyber security. The security of business systems and data is vital, and with most business having an online presence you will learn to implement AI to monitor and protect against cyber attacks.
With large scale cyberattacks becoming more common in recent years, artificial intelligence (AI) is key in watching for patterns that could indicate bots or other AI systems, blocking these attempts and keeping systems secured.
With an overwhelming majority of security vendors claiming to do some kind of artificial intelligence in their solutions – either to spot malicious behaviour patterns, or to add support to overloaded security operation centres – already AI is changing the methods of how most security vendors approach threat detection, and many would agree that AI in security is still in its infancy.
Our MSc Artificial Intelligence with Cyber Security course is designed to prepare you in the area of network, information and computer security, focusing on the strategic implementation of AI-enabled security methods. You will learn in a business-focussed context, allowing you to assess new and existing cyber security threats and apply suitable AI techniques to minimise them. Businesses will also have the opportunity to present you with real-life problems through our guest lectures, giving you an understanding of business needs in this area.
You will gain an awareness of the legal, economic, societal and ethical issues that an AI-based cyber security system might impact on, and the ability to implement IT strategies to conform to the appropriate professional, regulatory and ethical guideline constraints.
This course addresses the needs of network engineers, cyber security specialists and computer scientists who already have a relevant degree qualification and want to broaden their expertise through postgraduate studies in AI techniques applied to cyber security.
Once you have completed this course you will be prepared to undertake roles that require programming for data analysis, a knowledge of machine learning, neural networks and deep learning and also apply these skills specifically to cyber security.
If you’d like to continue your studies in research or further education, Anglia Ruskin offers a wide range of full-time and part-time postgraduate research degrees including MPhil or/and PhD in Computer Science, or even a DProf in Science and Technology.
MODULES & ASSESSMENT
Python and Data AnalysisThis module focuses on the use of Python programming for data analysis and provides you with the skills needed to complete artificial intelligence projects that are relevant for both industry and research. You will learn how to use Python programming to efficiently store and manipulate data as well as relevant data science tools that will enable you to start your own data analysis. You will be introduced to IPython as an interactive shell to be used as a primary development environment, will learn the basics and advanced features of NumPy (Numerical Python) and will create data visualisations with Matplotlib. This module will also introduce the Pandas library for data analysis. Finally, you will learn how to solve problems by incorporating all the elements reviewed in the module and apply them in different scenarios. This is a hands-on module where you will understand Python concepts through practical lectures and demonstrations and then apply them in a practical session. This module and will provide you with the necessary skills to use Python, as well as its different tools/libraries, to prepare data for data analysis, you are not expected to have previous experience with Python, but it is desirable to have programming experience.
Web Application SecurityWeb applications have reshaped business for the better by making e-commerce, online banking, and highly customised customer and partner portals possible. By moving business-critical applications and services like sales, support and purchasing to the Web, organisations have extended the boundaries of the enterprise—opening it up to enhance interaction with customers, suppliers, partners and employees. Web applications also speed and streamline internal processes. In other words, they deliver the benefit businesses are always looking for, from higher employee productivity and lower support costs to increased customer satisfaction and greater revenue. There is a serious consequence to this increased reliance on Web applications: they are inherently insecure and easily compromised. In fact, Gartner/NIST rates between 75 to 92 percent of vulnerabilities now occur in application rather than the network. Vulnerable Web applications not only put network systems and devices at much greater risk, they also offer a direct conduit to confidential customer data such as credit card numbers, account history and health records, as well as to sensitive corporate information. This module through the use of lecture material, online reading tools industry standard tools and practical lab exercises allow you to be able to critically analyse and appraise web applications from a penetrations tester point of view and be able interpret how security vulnerabilities impact web application design and operation. You will learn to evaluate web applications security risk levels and recommend appropriate mitigation controls.
Advanced Machine LearningMachine learning is a sub-discipline of the Artificial Intelligence that deals with teaching the computer to act without being programmed. In this module you will learn about the tools and algorithms that can be used to create machine learning models. Big data and their economic, legal and ethical aspects are explored, along with data acquisition and pre-processing methods that are used to make these suitable for machine learning algorithms. You will also look into how large data sets should be divided into a training set and a test set and different types of problems that can be solved with machine learning will also be introduced. A range of parametric algorithms such as linear regression, logistic regression, and non-parametric algorithms such as K-Nearest neighbour, decision trees, SVMs, will be discussed. To be able to evaluate a model, a few performance metrics will be explored, the metrics chosen influence how the performance of machine learning algorithms are measured and compared. An important concept that you have to be aware of when training machine learning algorithms is ‘overfitting’, an over fitted model will have a low accuracy and therefore you will learn how to use regularization to avoid overfitting.
Research MethodsGain support and foundations in the research skills needed for your Masters level dissertation. You’ll investigate research activities including project management, research project design and analyses, ethical considerations and dissertation preparation.
Cyber Security and AI Case StudiesHere you will consider how machine learning is being applied to modern cyber security and threat detection. You will be introduced to the tools and techniques in network and software application threat mitigation, and discuss how artificial intelligence is currently, or should be, used to support security analysts in their jobs. The practical sessions of this module are very hands-on and you will learn basic cyber penetration testing techniques and tools, through a series of weekly laboratory tasks. Penetration testing framework tools such as Kali, will be used to test both network and software applications for vulnerabilities. Throughout this module, you will be encouraged to consider how the tools and techniques covered could be applied to ideas for you Major Project. You are not expected to have previous experience with threat detection, but it is desirable to have an understanding of the OSImodel and network protocol handshakes, together with an understanding of how software applications are built. You are also not expected to have previous experience with penetration testing, but would benefit from having used Linux operating systems such as Debian.
Neural Computing and Deep LearningDeep learning and neural networks have revolutionised numerous fields in recent years. From smartphones and smart watches to cars and even house appliances, electronic devices are increasingly making use of machine learning and neural computing to take decisions, categorise and classify items, learn behaviours, assist us with choices and make prediction. The near future will see an even larger number of “self-learning” devices in almost every aspect of our lives. This module explores two main areas of Intelligent Systems: neural networks and deep learning. You will start analysing the structure of neural networks, from the theoretical aspects to the practical implementations, both biological and artificial. You will then move to the concept of supervised and unsupervised learning and analyse some of the most widely used deep learning methodologies. You will cover some of the main models and algorithms for regression, classification, clustering and decision making processes. The module will include applications of neural computing and deep learning to big data in physical and biological sciences, finance and social sciences. You will use primarily the Python programming language and requires familiarity with basic linear algebra, probability theory, and programming in Python.
Major ProjectThis module supports students in the preparation and submission of a Master’s stage project, dissertation or artefact. The Module provides the opportunity for students to select and explore in-depth, a topic that is of interest and relevant to their course in which they can develop a significant level of expertise. It enables students to: demonstrate their ability to generate significant and meaningful questions in relation to their specialism; undertake independent research using appropriate, recognised methods based on current theoretical research knowledge, critically understand method and its relationship to knowledge; develop a critical understanding of current knowledge in relation to the chosen subject and to critically analyse and evaluate information and data, which may be complex or contradictory, and draw meaningful and justifiable conclusions; develop the capability to expand or redefine existing knowledge, to develop new approaches to changing situations and/or develop new approaches to changing situations and contribute to the development of best practice; demonstrate an awareness of and to develop solutions to ethical dilemmas likely to arise in their research or professional practice; communicate these processes in a clear and elegant fashion; evaluate their work from the perspective of an autonomous reflective learner.
Throughout the course, we’ll use a range of assessment methods to measure your progress. You’ll complete exams, essays, research reports, oral presentations, and a dissertation on a subject of your choice.