Data-efficient Approaches to Responsible Model Deployment

Brief description of the context of the research including potential impact:
Deep learning methods have demonstrated exceptional performance in a wide range of tasks spanning various domains, becoming a ubiquitous part of our lives. While the promise of these models is substantial, the secure and efficient deployment of such models in real-world scenarios faces many challenges, including but not limited to vulnerability to adversarial attacks, out-of-domain generalization errors, and concerns about fairness. It is highly relevant to understand the nature of such vulnerability and develop computational methodologies to alleviate their effect on model performance.

Aims and Objectives:
In this project, the student will focus on developing statistical and computational methodologies that can identify, quantify, and mitigate model vulnerabilities in a data-efficient manner.
The project may also involve the development and adaptation of models for enhanced fairness, reliability and generalizability across various target domains and problem settings.

Novelty of the research methodology:
During the first stage of this project, the student would focus on identifying model vulnerability when facing adversarial attacks. The student will (1) investigate efficient generative model-based methods of synthesising segmentation adversarial examples and study their transferability across various target models of different architectures and/or (2) investigate the possibility of synthesising domain-agnostic and task-agnostic adversarial attacks.

Alignment with EPSRC's themes/strategies:
Understanding model behaviour under adversarial attacks is key to enhancing model robustness and building secure and resilient AI systems.
Facilitate responsible model deployment and ensuring that models can act as fair, secure and robust decision support tools may help create opportunities and improve outcomes
The student will investigate the utility of the aforementioned methodologies in computer vision as well as medical imaging, aiming at benefiting both everyday life experience as well as medical applications to promote health, ageing, and overall well-being.
Any companies or collaborators involved: None

AIMS's impact will be felt across domains of acute need within the UK. We expect AIMS to benefit: UK economic performance, through start-up creation; existing UK firms, both through research and addressing skills needs; UK health, by contributing to cancer research, and quality of life, through the delivery of autonomous vehicles; UK public understanding of and policy related to the transformational societal change engendered by autonomous systems.

Autonomous systems are acknowledged by essentially all stakeholders as important to the future UK economy. PwC claim that there is a £232 billion opportunity offered by AI to the UK economy by 2030 (10% of GDP). AIMS has an excellent track record of leadership in spinout creation, and will continue to foster the commercial projects of its students, through the provision of training in IP, licensing and entrepreneurship. With the help of Oxford Science Innovation (investment fund) and Oxford University Innovation (technology transfer office), student projects will be evaluated for commercial potential.

AIMS will also concretely contribute to UK economic competitiveness by meeting the UK's needs for experts in autonomous systems. To meet this need, AIMS will train cohorts with advanced skills that span the breadth of AI, machine learning, robotics, verification and sensor systems. The relevance of the training to the needs of industry will be ensured by the industrial partnerships at the heart of AIMS. These partnerships will also ensure that AIMS will produce research that directly targets UK industrial needs. Our partners span a wide range of UK sectors, including energy, transport, infrastructure, factory automation, finance, health, space and other extreme environments.

The autonomous systems that AIMS will enable also offer the prospect of epochal change in the UK's quality of life and health. As put by former Digital Secretary Matt Hancock, "whether it's improving travel, making banking easier or helping people live longer, AI is already revolutionising our economy and our society." AIMS will help to realise this potential through its delivery of trained experts and targeted research. In particular, two of the four Grand Challenge missions in the UK Industrial Strategy highlight the positive societal impact underpinned by autonomous systems. The "Artificial Intelligence and data" challenge has as its mission to "Use data, Artificial Intelligence and innovation to transform the prevention, early diagnosis and treatment of chronic diseases by 2030". To this mission, AIMS will contribute the outputs of its research pillar on cancer research. The "Future of mobility" challenge highlights the importance the autonomous vehicles will have in making transport "safer, cleaner and better connected." To this challenge, AIMS offers the world-leading research of its robotic systems research pillar.

AIMS will further promote the positive realisation of autonomous technologies through direct influence on policy. The world-leading academics amongst AIMS's supervisory pool are well-connected to policy formation e.g. Prof Osborne serving as a Commissioner on the Independent Commission on the Future of Work. Further, Dr Dan Mawson, Head of the Economy Unit; Economy and Strategic Analysis Team at BEIS will serve as an advisor to AIMS, ensuring bidirectional influence between policy objectives and AIMS research and training.

Broad understanding of autonomous systems is crucial in making a society robust to the transformations they will engender. AIMS will foster such understanding through its provision of opportunities for AIMS students to directly engage with the public. Given the broad societal importance of getting autonomous systems right, AIMS will deliver core training on the ethical, governance, economic and societal implications of autonomous systems.