The ability to innovate is a precious commodity that humans are well-disposed to accomplishing. Over the past 400 years in particular, humans have innovated with blistering pace, leading to the so-called developed world in stark contrast to other forms of innovation, such as evolution in the natural world that has been accomplished over a much slower time frame – billions rather than hundreds of years.
Currently, in the quest for development of artificial intelligence techniques that can support innovation, blueprints for how innovation occurs are an important ingredient. The study of how humans innovate has emerged within the field of “cultural evolution” [1] reaching the stage where explanations have emerged on how innovation takes hold through accumulation – progressively building on and sharing concepts, ideas and approaches that are shared and become a basis for subsequent improvements and novelty.
These observations on human innovation have an evolutionary character, but in contrast to evolution in nature, they are critically based on human bias – or the tendency to prefer something for a potentially arbitrary or intrinsic reason. These biases implement either social learning strategies or processes related to the inherent preferences of individuals and individual learning. Models for explaining human innovation as an evolutionary process offer a blueprint for innovation that can be followed in an algorithmic form by the machine [2].
This project aims to explore the impact of such approach to the area of cybersecurity, for example to generate innovative response strategies to cyberattacks and for automatic malware detection. Both scenarios implement variables representing specific actions and behaviours as input and populations of AI solutions in the form of artificial neural networks (ANN) can be maintained and evolved in parallel to either detect a malicious action or to suggest the system response to it as their output [3].
Instead of traditionally employed methodologies such as machine learning, these neuroevolutionary approaches allows the individual ANN solutions to target different objectives with the potential of transmitting and combining their knowledge in the form of their specific weights and topologies [4]. Objectives can be related to the specific problem considered, such as optimal response strategies and pre-emptive identifications of malicious behaviours but can also include intrinsic factors such as novelty and creativity [5,6]. Finally, elements of human innovation can be incorporated in their evolution in the form of the above-mentioned biases related to social learning and individual preference and learning [1,2].
If you wish to discuss the project further, contact [Email Address Removed]
Keywords: Cybersecurity / Artificial Intelligence / Human-Centred Computing / Neural Networks, Evolutionary Algorithms / Human Innovation.
Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas.
Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component.
How to apply:
Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below
Please submit your application before the application deadline 13th March 2023 via Computer Science and Informatics - Study - Cardiff University
In order to be considered candidates must submit the following information:
- Supporting statement
- CV
- In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD
- In the funding field of your application, insert “I am applying for 2023 PhD Scholarship in Computer Science and Informatics”, and specify the project title and supervisors of this project in the text box provided.
- Qualification certificates and Transcripts
- References x 2
- Proof of English language (if applicable)
If you have any questions or need more information, please contact [Email Address Removed]