Hummingbird: Human-machine integration for biometric authentication

Lead Research Organisation: University of Southampton
Department Name: School of Psychology

Abstract

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.

Planned Impact

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.
 
Description To follow at end of grant
Exploitation Route To follow
Sectors Aerospace, Defence and Marine,Government, Democracy and Justice,Security and Diplomacy

 
Description The findings will contribute to a major 5 year installation in the Winchester Science Centre's new Audio Zone. More details will follow on completion of grant.
First Year Of Impact 2019
Sector Aerospace, Defence and Marine,Education,Government, Democracy and Justice,Culture, Heritage, Museums and Collections,Security and Diplomacy
Impact Types Societal

 
Description Richard Guest and Sarah Stevenage gave evidence to the Parliamentary Office of Science and Technology for a POST note on the topic of biometrics and the policy issues it raises
Geographic Reach National 
Policy Influence Type Gave evidence to a government review
 
Description Richard Guest elected as member of the Biometrics and Forensics Ethics Group
Geographic Reach National 
Policy Influence Type Membership of a guideline committee
 
Description Steering Group Involvement 
Organisation Defence Science & Technology Laboratory (DSTL)
Country United Kingdom 
Sector Public 
PI Contribution Joint Project meetings
Collaborator Contribution Steering Committee membership
Impact n/a
Start Year 2018
 
Description Steering Group Involvement 
Organisation IBM
Department IBM UK Ltd
Country United Kingdom 
Sector Private 
PI Contribution Joint Project meetings
Collaborator Contribution Steering Committee membership
Impact n/a
Start Year 2018
 
Description Steering Group Involvement 
Organisation National Cyber Security Centre
Country United Kingdom 
Sector Public 
PI Contribution Joint Project meetings
Collaborator Contribution Steering Committee membership
Impact n/a
Start Year 2018
 
Description Contribution to Landscape Report on Iris Recognition 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Policymakers/politicians
Results and Impact Contribution to Landscape report on Iris Recognition
Year(s) Of Engagement Activity 2019
 
Description Contribution to POST publication: Biometrics: A Guide 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Policymakers/politicians
Results and Impact Contribution to Government Office for Science report.
https://www.gov.uk/government/publications/biometrics-a-guide
Year(s) Of Engagement Activity 2018
 
Description Government Briefing GO Science/POST Parliamentary Briefing on Biometrics - 6th February 2019 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Policymakers/politicians
Results and Impact Policy Briefing to Government Ministers
Year(s) Of Engagement Activity 2019
 
Description POST note on Emerging Biometric Technologies 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Policymakers/politicians
Results and Impact Contribution to POST note on Biometric Technologies
Year(s) Of Engagement Activity 2019
URL https://researchbriefings.parliament.uk/ResearchBriefing/Summary/POST-PN-0578#fullreport
 
Description Public Engagement Event 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Involvement in David Robertson's Public Engagement Event 'Are you are SuperRecogniser?' at the Explorathon, held at the Glasgow Riverside Museum, Friday 28th September 2018

David Robertson's workshop "Are You a Super Recogniser?" will give you the opportunity to find out if you never forget a face or voice. Some people are 'Super Recognisers', and the Metropolitan Police use officers with this extraordinary ability to identify criminals from CCTV images or voice recordings. During David's workshop, you will be able to take part in real psychology studies by completing quick computer recognition tasks. You can even find out if you too are a 'Super Recogniser' by comparing your scores to the officers in the Metropolitan Police! You can also take on the role of a Border Control Officer and try matching faces to passport photos, try his "Before They Were Famous" face test, and see how you will age with David's iPad app demonstration.
Year(s) Of Engagement Activity 2018
URL http://www.explorathon.co.uk/events/explorathon-extravaganza/
 
Description SOTSEF 2019 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Science and Engineering Festival 2019 at the University of Southampton
Year(s) Of Engagement Activity 2019