Privacy-Protected Human Identification in Encrypted/Transformed Domains
Lead Research Organisation:
Lancaster University
Department Name: Computing & Communications
Abstract
Biometrics has been widely utilized in the past two decades in many areas such as healthcare, banking, surveillance, and security control. Given the increased uptake of internet and mobile computing globally, many companies have been turning to biometric privacy and security to ensure secure communication. However, biometric verification over third-party or public network servers may be abusively exploited in an unauthorized way. To protect the privacy and improve the security, it has been advocated to carry out biometric verification in encrypted or transformed domains, where privacy and security can be more effectively guaranteed.
The basic idea behind the project is that the biometrics in the irreversible encrypted/transformed domains contains exactly the same amount of information as its original one, and hence one can establish a pattern recognition methodology to determine/extract useful information from chaotic signals in encrypted/transformed domains. This First Grant Scheme project aims to investigate how to discover and evaluate the information from chaotic signals for discriminative power, and develop robust pattern recognition schemes for biometric/multi-biometric verification in encrypted/transformed domains. The proposed methods/schemes will be vigorously validated over typical wild face/speech/gait datasets, and two practical demo systems (biometric banking and pedestrian profiling) will be designed and tested in real world environments.
The project will focus on both theoretical understanding of chaotic information and application-specific exploitation of chaotic pattern recognition. Considering multiple data structures hidden beneath a set of given chaotic signals, I will develop a robust way to find out the underlying various data structures for data understanding, clustering and classification. On the other side, given a specific issue such as encrypted/transformed biometric verification, one need to examine the generic theoretic findings in this specific topic and develop a robust scheme for biometric human identification.
The work of this project is within the areas of signal processing, machine learning and pattern analysis. The research on encryted/transformed biometric verification has come from the practical new needs of the UK's emerging new businesses. The project will provide the understanding needed to allow the future development of robust biometric verification methods with novel applications.
The basic idea behind the project is that the biometrics in the irreversible encrypted/transformed domains contains exactly the same amount of information as its original one, and hence one can establish a pattern recognition methodology to determine/extract useful information from chaotic signals in encrypted/transformed domains. This First Grant Scheme project aims to investigate how to discover and evaluate the information from chaotic signals for discriminative power, and develop robust pattern recognition schemes for biometric/multi-biometric verification in encrypted/transformed domains. The proposed methods/schemes will be vigorously validated over typical wild face/speech/gait datasets, and two practical demo systems (biometric banking and pedestrian profiling) will be designed and tested in real world environments.
The project will focus on both theoretical understanding of chaotic information and application-specific exploitation of chaotic pattern recognition. Considering multiple data structures hidden beneath a set of given chaotic signals, I will develop a robust way to find out the underlying various data structures for data understanding, clustering and classification. On the other side, given a specific issue such as encrypted/transformed biometric verification, one need to examine the generic theoretic findings in this specific topic and develop a robust scheme for biometric human identification.
The work of this project is within the areas of signal processing, machine learning and pattern analysis. The research on encryted/transformed biometric verification has come from the practical new needs of the UK's emerging new businesses. The project will provide the understanding needed to allow the future development of robust biometric verification methods with novel applications.
Planned Impact
The rapid advancement in biometric technology has generated huge impact in UK's usual life, ranging from financial service, public security, legal service, immigration control, to daily medical service and healthcare. As a result, biometric industry in UK has experienced drastic expansion in its market. For example, biometric banking has been widely endorsed by major UK banks. Public surveillance is also becoming a thriving market in UK. The value of new biometric markets has achieved $15 billion in 2015 and been estimated to grow further to $45 billion by 2021 (Global Biometrics Market, Markets & Markets, 2015). However, accompanying with the wide spread of biometric uses, people are more and more concerned about its security and privacy issues, especially when Internet-of-Things becomes booming and biometrics are used over public network severs. Developing safe and robust biometric technologies is a key priority for the UK to maintain and reinforce its world-leading role in this new research area and business market.
A key sector in the UK economy is banking and financial services, which accounts for 10% GDP (Financial services industry of the United Kingdom, Wikipedia) and 33% of the UK's trade balance. Biometric banking is now growing in importance due to the increased popularity and spread of mobile banking. People can easily access their accounts by scanning their face/iris/fingerpring. In the past two years, biometrics such as fingerprints/veins have been utilized by major banks such as HSBC and Barclays. Atom Bank has developed a solution to exploit face and voice recognition, which can be more conveniently integrated with mobile banking. This project will address key security and privacy issues linked to mobile banking, and Atom's involvement will give invaluable insight into industrial requirements for advanced technology exploiting biometric verification in the encrypted domain. I will also develop a mobile-based biometric banking demo with Atom Bank's professionals. Atom bank is a potential partner for future spin-off projects funded directly (under non-disclosure agreements), via InnovateUK (KTPs or otherwise) or with other partners in, for example in EU Horizon 2020 projects.
Public surveillance is another UK's thriving industry with a market value estimated around £6 billions (Securing the Nation's Future, British Security Industry Association). In this project, I will develop a surveillance demo system in collaboration with Warwick team and their spin-out, which is about pedestrian profiling using scrambled gait/face to provide real-time city monitoring on google map. Potentially, this may lead to a further KTP project via InnovateUK or a SME project via EU Horizon 2020.
The training of the postdoctoral researcher and a university funded PhD student with skills relevant to digital technologies will benefit both the individuals and UK industry. The experience gained will include signal processing, artificial intelligence, vision and image, and security systems. They will receive training in public understanding and engagement and will be involved in outreach work through Think Physics and Digital Living activities and attend exhibitions at Sunderland Software Cities and North East Catapult Centre (Sunderland). This will benefit the individuals and also attract wider interest from the public by promoting the spirit of science and highlighting everyday impacts which arise from this research.
A key sector in the UK economy is banking and financial services, which accounts for 10% GDP (Financial services industry of the United Kingdom, Wikipedia) and 33% of the UK's trade balance. Biometric banking is now growing in importance due to the increased popularity and spread of mobile banking. People can easily access their accounts by scanning their face/iris/fingerpring. In the past two years, biometrics such as fingerprints/veins have been utilized by major banks such as HSBC and Barclays. Atom Bank has developed a solution to exploit face and voice recognition, which can be more conveniently integrated with mobile banking. This project will address key security and privacy issues linked to mobile banking, and Atom's involvement will give invaluable insight into industrial requirements for advanced technology exploiting biometric verification in the encrypted domain. I will also develop a mobile-based biometric banking demo with Atom Bank's professionals. Atom bank is a potential partner for future spin-off projects funded directly (under non-disclosure agreements), via InnovateUK (KTPs or otherwise) or with other partners in, for example in EU Horizon 2020 projects.
Public surveillance is another UK's thriving industry with a market value estimated around £6 billions (Securing the Nation's Future, British Security Industry Association). In this project, I will develop a surveillance demo system in collaboration with Warwick team and their spin-out, which is about pedestrian profiling using scrambled gait/face to provide real-time city monitoring on google map. Potentially, this may lead to a further KTP project via InnovateUK or a SME project via EU Horizon 2020.
The training of the postdoctoral researcher and a university funded PhD student with skills relevant to digital technologies will benefit both the individuals and UK industry. The experience gained will include signal processing, artificial intelligence, vision and image, and security systems. They will receive training in public understanding and engagement and will be involved in outreach work through Think Physics and Digital Living activities and attend exhibitions at Sunderland Software Cities and North East Catapult Centre (Sunderland). This will benefit the individuals and also attract wider interest from the public by promoting the spirit of science and highlighting everyday impacts which arise from this research.
People |
ORCID iD |
Richard Jiang (Principal Investigator) |
Publications
Jiang Z
(2023)
Delve Into Neural Activations: Toward Understanding Dying Neurons
in IEEE Transactions on Artificial Intelligence
Shahzad M
(2022)
EBSRMF: Ensemble based similarity-regularized matrix factorization to predict anticancer drug responses
in Journal of Intelligent & Fuzzy Systems
Easom-McCaldin P
(2024)
Efficient Quantum Image Classification Using Single Qubit Encoding.
in IEEE transactions on neural networks and learning systems
Longo L
(2024)
Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions
in Information Fusion
Shen A
(2024)
Marine Debris Detection in Satellite Surveillance Using Attention Mechanisms
in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Cheheb I
(2021)
Multi-Descriptor Random Sampling for Patch-Based Face Recognition
in Applied Sciences
Easom-Mccaldin P
(2021)
On Depth, Robustness and Performance Using the Data Re-Uploading Single-Qubit Classifier
in IEEE Access
Hardy J
(2021)
Potential for Chemistry in Multidisciplinary, Interdisciplinary, and Transdisciplinary Teaching Activities in Higher Education
in Journal of Chemical Education
Description | So far, from the project, we have following key findings. 1) The encrypted/scrambled biometrics, though similarly chaotic as noises in their signals, contain sufficient information for classification. Hence, such encrypted/biometric patterns can be used as their original ones for identification verification, with little compromise on accuracy. 2) So far we tested new methods such as DAE and CNNs. DAE can work well on these chaotic patterns, but CNNs have drastic drops on their accuracy when handling the scarmbled/encrypted patterns. 3) A novel information measure is developed to measure the amount of information in such chaotic patterns. 4) A set of datasets were prepared and will be publically avalable for the research community. 5) The above findings will be published subsequently in 2020. |
Exploitation Route | Further research bids were submitted to EPSRC to implement the privacy-protected face-based passenger screening for security purpose, jointly with industry partners. |
Sectors | Digital/Communication/Information Technologies (including Software) Electronics Financial Services and Management Consultancy Healthcare Government Democracy and Justice Security and Diplomacy Transport |
Description | Face2Gene: Genetic Identity behind Deep Facial Features |
Amount | £46,000 (GBP) |
Organisation | The Leverhulme Trust |
Sector | Charity/Non Profit |
Country | United Kingdom |
Start | 03/2020 |
End | 02/2021 |
Description | Biometrics-based Mobile Banking with Atom Bank |
Organisation | Atom Bank |
Country | United Kingdom |
Sector | Private |
PI Contribution | The initial collaboration between my team and Atom Bank has been reinforced by this EPSRC project. A number of meetings and joint actions have been planned and hopefully, this will enable our novel research on biometrics for Atom Bank's mobile banking service. |
Collaborator Contribution | Atom bank has kindly shared their experience on commercialized mobile banking services with us, making our research more tightly bound with the needs of the financial industry. |
Impact | The partner has provided their support letter to our EPSRC bidding and promise nearly £20k in-kind support to our research. |
Start Year | 2016 |
Description | Human Activity Analysis in Smart Cities |
Organisation | University of Warwick |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Collaboration with Professor Chang-tsun Li in Computer Science, Warwick University, on Human Activity Analysis. |
Collaborator Contribution | Provide key support on developing joint research and producing papers on relevant topics. Also help organize a Springer book and special issue (in preparation) about the core research topics in this project. |
Impact | Two co-edited Springer books on biometrics and smart cities are under press (2019 - 2020). |
Start Year | 2017 |