Hummingbird: Human-machine integration for biometric authentication

We live in a technological age in which we can use our voice as a password to access online banking, and our children can pay for school lunches with a fingerprint. Biometrics, which reflect our physiological or behavioural characteristics, are now common as a way to prove our identity in order to access secure information, services or spaces. Given the important uses associated with biometrics, there is a fundamental need for accuracy in biometric analysis in order to encourage trust amongst both citizens and service providers. The feasibility study undertaken within the HUMMINGBIRD project will provide a human-inspired framework to address both needs.

The recent publication of two high profile report converge to make this endeavour timely and necessary. The first is the UK Governmental review on 'Future Identities', which recognised the transformative effect that digital technologies are having on identity. In particular, it noted the myriad of ways we now have to convey our identity, and to have it spoofed. The second is the UK Parliamentary Select Committee review on 'The Current and Future Uses of Biometrics' which highlighted two necessary future steps for biometric analysis: Analysis should draw on behavioural as well as physiological measures; and it should take full advantage of the combination of data across multiple biometrics and across decision makers in order to improve decision-making.

To address all factors, we propose an exciting project that will deliver a human-inspired multi-expert, multi-modality framework for biometric analysis. This will satisfy three aims: First, it will deliver enhanced algorithms for automated biometric analysis by incorporating successful strategies used by humans. Second, it will deliver a method of combining decisions made by humans and (enhanced) algorithms in order to boost accuracy. Third, it will deliver the potential to combine multiple biometrics, providing resilience in scenarios in which a single modality may be sub-optimal.

The HUMMINGBIRD project team possesses a unique combination of skills to explore this idea and indeed, we build on recently published theoretical work on this topic. In this proposal, we examine two biometrics - face and voice - which reflects the move to combine static physiological measures (facial images) and dynamic behavioural measures (temporal voice samples). We also concentrate on two decision-makers - the human and state-of-the-art automated algorithm - providing direct relevance to scenarios in which the human must be part of the decision-process (such as in forensic decisions). Our work will establish the fundamental performance levels of humans and machine algorithms when recognising faces and voices under optimal and sub-optimal presentation conditions. It will then seek to enhance the machine algorithms through incorporation of human rules and heuristics. Such a move offers the potential to boost accuracy and efficiency by streamlining automated solutions. More importantly, it exploits the fact that humans can outperform machine algorithms under some conditions, such as when trying to recognise a face under dim light, or a voice amidst noise. Finally, our work will apply an innovative data fusion model to combine the decisions of humans and machine algorithms from one biometric, and then from multiple biometrics. This novel and creative element of our work addresses issues of accuracy, disagreement resolution, and resultant confidence in an identity decision, when the situation is inherently uncertain.

Arguably, biometrics reflect identity more directly than token or password systems because they rely on who we are rather than what we have or know. As such, biometric analysis is likely to remain a mainstay of identity management. The HUMMINGBIRD project presents real promise as a way to improve accuracy and confidence in that analysis, enabling accuracy of, and trust in, identity management as technology advances.

The HUMMINGBIRD project addresses the priority area of human identification through biometric analysis. Success in this area is paramount if the benefits of modern living are to be fully realised. For example, systems that accurately verify our identity allow us to move seamlessly through secure spaces such as work areas or airport boarding gates. Moreover, proof of our identity allows us to access e-systems such as online banking and eCommerce. Biometrics now provide an integral element to enable human identification. However, there are concerns regarding reliability of the automated systems responsible for biometric analysis. The HUMMINGBIRD project aims to enhance biometric analysis through application of a novel human-like computing approach.

Key societal and economic impacts are anticipated from the HUMMINGBIRD project, and several stakeholder groups have been identified, including citizens, as well as government and industry parties. Civic interest stems from a need on the part of the public to be assured of reliable means to prove their identity, and to protect their identity from misuse or spoofing. This requires that the tools we use are optimised for the job at hand, in a way that allows the intelligent combination of information across multiple measures and across multiple decision-makers. The HUMMINGBIRD project explores a novel framework to achieve exactly this. First, we seek to enhance machine analysis by integrating successful human strategies. Second, we seek to improve reliability by combining human and machine decision makers into the final decision. Third, we seek to improve resilience by incorporating more than one biometric measure into the identity decision. It is anticipated that the improved performance of the system, and the transparency gained through human involvement, will increase both accuracy and trust, and will boost civic confidence, particularly within low-throughput, high-risk scenarios. Within this feasibility study, our involvement with, and feedback to, civic groups comes through our dialogue with human participants, and our dissemination plans via science fairs, museum exhibits, media reports, and social media channels.

Societal impact will also be felt by government and industry stakeholders. Government agencies are especially interested in biometric identification, as evidenced through ongoing debate of the new Identity Assurance schemes, and the introduction of novel technologies such as eGates into UK airports. Within the forensic sector too, the Chief Scientific Advisor's report on 'Forensic Science', and the GO Science report on 'The Current and Future Uses of Biometrics', both published within the last 2 years, witness the continued interest in biometric analysis. The HUMMINGBIRD project will provide clear benefit, through contribution to governmental understanding and capability. This will be delivered through knowledge transfer channels, both through active Steering Committee involvement and dissemination to wider government groups. Alongside this, Industry interest centres on the practical question of how to deliver an identity management solution which combines user acceptability with a minimum of error. The relationship between the HUMMINGBIRD project and IBM as a hub for Emerging Technologies, provides a clear route to deliver benefit in a way that is ahead of the technology curve.

Finally, the HUMMINGBIRD project is also likely to support sustained economic impact for UK wealth and technology through renewed public trust in e-Commerce and digital business. Inward investment will enable an improvement in UK competitiveness within a digital marketplace. Indeed, through providing the scaffolding for increased reliability, transparency and resilience of identity management, technologies may emerge in diverse areas such as mobile phone providers, eHealthcare systems, social media platforms, and online banking that make a material difference to modern living.