The annual report from Internet Crime Complaint Centre (IC3) states that Internet-enabled theft, fraud, and exploitation remain pervasive and were responsible for a staggering $2.7 billion in financial losses in 2018. Besides traditional efforts from computing network, cryptography, and social engineering, Artificial intelligence (AI) and Machine Learning (ML) are increasingly becoming a necessity for tackling cybersecurity challenges.
The effectiveness of intelligent defending techniques over cyber attacks does not stay long, as attackers are also using AI to swing the advantage of defending techniques back to their side. By analysing existing intelligent defending techniques, cyber attacks have been evolving to avoid being detected. For instance, in order to bypass spam filter, messages could be obfuscated through the misspelling of “bad” words or the insertion of “good” words. In such cases, the defending models proposed based on previous attacking patterns would not work for upcoming attacks anymore. Therefore, modern defenders should be able to model the evolution of attacking patterns and change their defending techniques adaptively.
This project will tackle this problem using Adversarial Machine Learning – a new ML paradigm which will take the interaction between attackers and defenders into account in addition to the historic attack data. We will first investigate the vulnerabilities of current intelligent defending techniques, and then develop the corresponding countermeasures using Adversarial Machine Learning techniques, which need to be further improved to be future proof.
A successful candidate should have solid knowledge in ML, computer science and cyber security. Good programming skill is required, and knowledge in mathematics is a plus. Strong candidates with a degree in computer science, electrical engineering, or related subjects will be considered. Candidates with relevant research background will be preferable. Excellent written and oral communication skills are essential.
This project is supervised by Dr Hua Mao. The second supervisor will be Dr Li Zhang.
Please note eligibility requirement:
• Academic excellence of the proposed student i.e. 2:1 (or equivalent GPA from non-UK universities [preference for 1st class honours]); or a Masters (preference for Merit or above); or APEL evidence of substantial practitioner achievement.
• Appropriate IELTS score, if required.
• Applicants cannot apply for this funding if currently engaged in Doctoral study at Northumbria or elsewhere.
For further details of how to apply, entry requirements and the application form, see https://www.northumbria.ac.uk/research/postgraduate-research-degrees/how-to-apply/
Please note: Applications that do not include a research proposal of approximately 1,000 words (not a copy of the advert), or that do not include the advert reference (e.g. RDF20/EE/CIS/MAO) will not be considered.
Deadline for applications: Friday 24 January 2020
Start Date: 1 October 2020
Northumbria University takes pride in, and values, the quality and diversity of our staff. We welcome applications from all members of the community. The University holds an Athena SWAN Bronze award in recognition of our commitment to improving employment practices for the advancement of gender equality.
1. Yu Wu, Hua Mao, Zhang Yi: Audio classification using attention-augmented convolutional neural network. Knowledge-Based Systems. 161: 90-100 (2018)
2. Tao He, Hua Mao, Jixiang Guo, Zhang Yi: Cell tracking using deep neural networks with multi-task learning. Image Vision Computing. 60: 142-153 (2017)
3. Yangxu Wang, Hua Mao, Zhang Yi: Protein secondary structure prediction by using deep learning method. Knowledge-Based Systems. 118: 115-123 (2017)
4. Yao Zhou, Hua Mao, Zhang Yi: Cell mitosis detection using deep neural networks. Knowledge-Based Systems. 137: 19-28 (2017)
5. Jiali Yu, Hua Mao, Zhang Yi: Parameter as a Switch Between Dynamical States of a Network in Population Decoding. IEEE Transactions on Neural Networks and Learning Systems. 28(4): 911-916 (2017)