Towards Robust Machine Learning with Deep Neural Networks using 3D Data
Despite their significance in enhancing vision-based tasks such as classification and recognition, deep neutral networks are vulnerable to carefully crafted adversarial attacks. In other words, delicately designed neural networks with high performance can be easily fooled by an unnoticeable perturbation on the original data. In addressing the above concern, researchers have extensively investigated adversarial attacks on 2D images by simply perturbing pixel values. In contrast, adversarial attacks on 3D shapes are much less explored. This is largely due to the fact that 3D shapes with arbitrary geometry and topology do not have a regular parameter domain that can be directly learned by deep neural networks. Intermediate representations (e.g., voxel grids, multi-view projections, point samples) are required to enable the learning process. In this project, we would like to comprehensively study the robustness of different representations for 3D classification and recognition, and further investigate how to improve the reliability of deep neural networks under adversarial attacks. This would benefit a number of important applications which require robust 3D data understanding, such as autonomous driving and medical imaging.
This project is associated with the UKRI CDT in Accountable, Responsible and Transparent AI (ART-AI), which is looking for its second cohort of at least 10 students to start in September 2020. Further details can be found at: http://www.bath.ac.uk/centres-for-doctoral-training/ukri-centre-for-doctoral-training-in-accountable-responsible-and-transparent-ai/.
Applicants should hold, or expect to receive, a First or Upper Second Class Honours degree. A master’s level qualification would also be advantageous.Desirable qualities in candidates include intellectual curiosity, a strong background in maths and programming experience.
Informal enquiries about the project should be directed Dr Yongliang Yang on email address [Email Address Removed].
Enquiries about the application process should be sent to [Email Address Removed].
Formal applications should be made via the University of Bath’s online application form: https://samis.bath.ac.uk/urd/sits.urd/run/siw_ipp_lgn.login?process=siw_ipp_app&code1=RDUCM-FP02&code2=0002
Start date: 28 September 2020.
ART-AI CDT studentships are available on a competition basis for UK and EU students for up to 4 years. Funding will cover UK/EU tuition fees as well as providing maintenance at the UKRI doctoral stipend rate (£15,009 per annum in 2019/20, increased annually in line with the GDP deflator) and a training support fee of £1,000 per annum.
We also welcome all-year-round applications from self-funded candidates and candidates who can source their own funding.
 He Wang, Feixiang He, Zhexi Peng, Yongliang Yang, Tianjia Shao, Kun Zhou, David Hogg. SMART: Skeletal Motion Action Recognition aTtack. arXiv, abs/1911.07107, 2019.
 Akhtar, Naveed and Mian, Ajmal. Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey. IEEE Access. 10.1109/ACCESS.2018.2807385. 2018
How good is research at University of Bath in Computer Science and Informatics?
FTE Category A staff submitted: 24.00
Research output data provided by the Research Excellence Framework (REF)
Click here to see the results for all UK universities