FindAPhD Weekly PhD Newsletter | JOIN NOW FindAPhD Weekly PhD Newsletter | JOIN NOW

Security Vulnerabilities and Protection in Approximate Computing


   School of Electronics, Electrical Engineering and Computer Science

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Dr Chongyan Gu, Prof M O'Neill  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

As Moore’s law is approaching its limit, conventional computing techniques are struggling to offer high computing performance within power consumption constraints. One of the most promising directions over traditional computing for energy-efficient system is “approximate computing”, which is reported as one of top ten technologies to change the world. Leading companies are undertaking research into potential products and services based on approximate computing. For example, Google’s deep learning (DL) chip achieves a significant improvement in Tensor Processing Unit (TPU) processing performance using common approximate computing techniques, such as precision scaling. Recently, IBM research has launched a project of building on-chip AI accelerators with approximate computing techniques. However, recently approximate computing has been shown vulnerable to some attacks, such as malicious modifications and hardware Trojan attacks. To address this, this project explores the potential of emerging digital technologies, such as hardware security, machine learning and approximate computing, to transform the way we design, manufacture, and operate products and services. The programme offers a bespoke research and training programme that aims to develop students into cross-disciplinary, industry-conscious thinkers and leaders who will influence the roadmaps of future advanced technologies and their applications. They will have a balanced understanding of ICT (security and data analytics) in the context of their application to advanced technologies and high value designs.

Project Description:

Approximate computing is error-tolerant, offering up to an order of magnitude reduction in power consumption. Inspired by the fault tolerance capability of the human brain, approximate computing can accept errors in calculation without affecting the results of certain human perception and recognition related computation, including AI, deep learning (DL), machine learning (ML), signal processing and even some cryptographic schemes, in which noisy data, redundant information, and inaccurate results are tolerable for the computation. However, approximate computing may be introduced security vulnerabilities due to the unpredictability of intrinsic errors during approximate execution that may be indistinguishable from malicious modifications. If vulnerabilities are introduced via approximate computing techniques, the applications in which they are utilized will inevitably be affected. To achieve approximate designs that are secure it will be necessary to investigate how to differentiate errors introduced by the approximate computing from malicious errors. A major challenge is to how to address the need for ensuring security while improving system efficiency in approximate computing. Most of the existing work on the vulnerability of, and attacks to, approximate computing have countermeasures as well. However, their main contribution is on the discovery of new vulnerabilities and attacks. The countermeasures are normally simple and straightforward. Therefore, non-trivial approaches on how to design and evaluate new countermeasures that are effective and robust against more sophisticated attacks will be needed. Since the advantages of approximate computing is the reduction in energy consumption and/or improvements in speed, the countermeasures must be low-cost and efficient. To address all these challenges, this project will investigate the security vulnerabilities in approximate computing techniques and develop novel hardware security-based designs to secure future advanced computing architectures (especially approximate computing) and maximizing the physical security requirement of hardware devices, especially for resource-constrained applications.

Project Key Words

Approximate computing, hardware security, resource-constrained applications.

Start Date: 01/10/22

Application Closing date: 28/02/22

For further information about eligibility criteria please refer to the DfE Postgraduate Studentship Terms and Conditions 2021-22 at https://go.qub.ac.uk/dfeterms

Applicants should apply electronically through the Queen’s online application portal at: https://dap.qub.ac.uk/portal/

Academic Requirements:

A minimum 2.1 honours degree or equivalent in Computer Science or Electrical and Electronic Engineering or relevant degree is required.

Funding Notes:

This three year studentship, for full-time PhD study, is potentially funded by the Department for the Economy (DfE) and commences on 1 October 2022. For UK domiciled students the value of an award includes the cost of approved tuition fees as well as maintenance support (Fees £4,500 pa and Stipend rate £15,609 pa - 2022-23 rates to be confirmed). To be considered eligible for a full DfE studentship award you must have been ordinarily resident in the United Kingdom for the full three year period before the first day of the first academic year of the course.

For candidates who do not meet the above residency requirements, a small number of international studentships may be available from the School. These are expected to be highly competitive, and a selection process will determine the strongest candidates across a range of School projects, who may then be offered funding for their chosen project.

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs