Joël Di Manno, Authentication & Biometrics Laboratory Service Line Manager and Abdarahmane Wone, Biometrics & AI Researcher at Fime.

User adoption of biometric authentication has accelerated in recent years, yet some users are still cautious. Fime is exploring ways to innovate on biometric evaluation to help solution providers to launch reliable and high-performance products. In this interview, Stéphanie Pietri, Communications Director at Fime, speaks to Joël and Abdarahmane about their scientific paper to learn more on the impact of environmental conditions on fingerprint systems performance.

Stéphanie Pietri: What is biometric authentication?

Joël Di Manno: Biometric authentication solutions utilize a person’s physical or behavioural characteristics, such as their fingerprint, face, or keystroke dynamics to verify their identity. Using biometric characteristics to authenticate someone provides a high level of security because these traits are unique to that person. It also provides a good user experience, as there is no need to remember long passwords. This can provide consumers with easier routes to make a payment or access a service.

However, the adaptability of biometric solutions can present challenges, as different conditions have the potential to increase false acceptance or rejection rates. This means that there is the potential for security to be compromised if non-genuine users can be verified, or the user experience will be impacted if genuine users cannot.

SP: What type of environmental conditions can influence biometric authentication?

Abdarahmane Wone: One of the challenges of biometric solutions is that environmental conditions can alter their performance. For example, if someone is using a facial recognition solution, changes in lighting or the background can influence its performance. Similarly, fingerprint systems can be affected when environmental conditions like temperature and humidity change, because the texture of fingerprints alter accordingly. This change can mean that the fingerprint does not match the reference fingerprint that was recorded during enrolment and therefore is not verified.

These environmental changes impact the performance, security, user experience and the trust of biometric systems. It is also important to note that not all biometric systems are impacted in a similar way. However, while we know that there is an impact, very little research has been done to assess the performance of biometric systems in different climatic environments.

SP: What did Fime do?

AW: To find out more about these impacts, Fime undertook some research to understand how humidity and temperature changes affect the performance of fingerprint systems. We tested the performance of three different third-party fingerprint authentication matchers in different climatic conditions. The aim was to see how accurate the algorithms were at matching the fingerprint samples taken during enrolment. The performance of the biometric systems was evaluated in six different conditions made up of a combination of two different temperatures and three different humidity environments. The different humidity and temperature environments were created using climatic chambers. After signing consent forms regarding European GDPR regulation, more than one thousand fingerprint images were collected from 17 volunteers.

SP: And what was the impact of these environmental factors on biometric authentication?

AW: We observed that all of the algorithms performed better when the environment was less humid. Importantly, we saw that the three algorithms were all impacted differently by temperature and humidity changes, demonstrating that the impact of environmental factors is not consistent across biometric solutions.

Also, the environmental conditions of the enrolment of the fingerprint samples made a difference. The algorithms all performed better when the environmental conditions were the same as those during enrolment of the fingerprint samples. Again, we saw that the three products were all impacted differently when the verification was done in an environment different to the enrolment environment. While two of the products differed less than 1%, the third product differed by 24%. This shows that the product could present high security risks and/or a bad user experience for consumers. This study highlights the importance of a comprehensive enrolment guide for vendors and users, to decrease the impact of environmental conditions as much as possible.

SP: What can be done to mitigate the impact of these conditions on biometric authentication systems?

JDM: Fime has now developed a process and identified parameters to evaluate environmental impact, thanks to the research project. The results of this research demonstrate that environmental conditions can have differing degrees of impact on biometric authentication systems. Therefore, testing the performance of biometric solutions in different environments, including different conditions between enrolment and verification, could prevent real-life issues. Certification schemes could introduce this aspect into their evaluation programs to ensure security in various conditions and decrease variance between different biometric solutions.

Biometric solution vendors can use this evaluation during their own quality assurance processes. By performing testing in this area, they can fine-tune solutions to mitigate the impact of environmental conditions. This will verify that their products can be deployed globally and will perform well in different climates. By taking these factors into consideration, they can enhance the trust, security, performance and user experience of their solutions. This may give them the ability to outperform competitors who are not considering the impact of environmental factors when developing their solutions.

Responses provided by Jerome Kemp, President, Baton Systems

Q. Organisations are forecast to spend nearly $6.6 billion on blockchain solutions this year, an increase of more than 50% compared to 2020, according to a new update to the International Data Corporation (IDC) Worldwide Blockchain Spending Guide. What does 2022 have in store for adoption of DLT? 

Since 2019, there has been a doubling of spending on DLT related developments. While the evolution in cloud computing transformed how we now store and access data, DLT has the potential to completely revolutionise collaborative interaction between market participants.

The high levels of funding pouring into this space is fueling unstoppable momentum, and I expect we will see this expressed in a number of ways as we cross the threshold into the new year.

We are acutely aware at Baton that interoperable DLT offers considerable possibilities relative to the existing post-trade landscape – possibilities that are now proving far too compelling to ignore. We’re in a situation today where trillions of dollars of financial assets change hands daily across very complex and aging infrastructures that consume massive amounts of financial and human resources. DLT has the potential to completely transform these aging technology stacks offering flexibility, transparency, security, resiliency and immutability, along with automation and collaboration.

2022 will be the year where we will start to see DLT being adopted by leading global financial institutions to address the long-standing risk, efficiency and transparency issues that have plagued post-trade processing for far too long, delivering a level of transformation that’s well overdue.

Q. What pinch points and obstacles will the post-trade sector still experience in 2022? 

The attraction of DLT as a means of transforming post-trade processing is undeniable. However, as is the case with any new approach to an age-old problem, DLT will likely continue to be scrutinised, analysed, and treated with a degree of skepticism by the market given its potential to displace existing platforms and network protocols that play a systemically important role in global market infrastructures.

The pace of technological innovation has outpaced the existing regulatory framework and while we see numerous levels of engagement from regulators around the world, the question of if, and then how, these new innovations should be regulated is now a source of regulatory debate.

Q. With the FX industry being rife with opportunities for modernisation – in what ways should it modernise in 2022 and in what ways will it modernise in 2022?

It’s not so much a question of how firms should modernise, as many are already undertaking multiple initiatives to do so. I think it’s more a case of firms really considering what they need to be doing today as the industry continues to rapidly evolve. The FX market has witnessed significant change in recent years, partially as a result of the significant increase in trading volumes and margin declines – and while the trading ecosystem has benefited from significant technology investment we are now seeing a notable shift to the post-trade processing space.

The focus now needs to switch to building fully-connected, seamless workflows from the point of execution through to settlement, so market participants have at their fingertips the flexibility to automate netting sets and to settle on demand with whomever they wish based on a number of criteria. It will be through the adoption and embrace of new technologies like DLT that market participants will be able to achieve the goal of performing riskless settlement on demand in virtually any currency and with any counterparty they choose.

Q. What are the big opportunities for the sector in 2022 with emerging technologies? 

Settlement risk has plagued the FX industry for far too long and I believe 2022 will see the adoption of emerging technologies that for the first time, will really allow firms to take control. There will be an opportunity to improve transparency through the end-to-end process from trade matching to settlement and as risk has such a huge impact on capital usage, eliminating sources of exposure would allow firms to optimise the deployment of funding and intraday liquidity management.

Q. Do you think the CBDCs will play a greater role next year? If so, how?

A growing proportion of the world’s central banks are now actively researching CBDCs and we’re seeing a number of individual experiments with real potential – all of which indicates a very real intention by central banks to systematically move forward with CBDC’s. In the US for example you have the digital dollar project, one of the major initiatives that is underway right now, it’s under the stewardship of J. Christopher Giancarlo, former CFTC chair and Senior Advisor to Baton.

Though I think that we have more ground to cover before we will start to see CBDCs emerge as an integral part of the business as usual (BAU) financial landscape this is an exciting and natural progression in the broader history of money, given the technologies that we are now able to leverage for the greater common good.

I also feel that the CBDC debate will be closely related to the position that regulators ultimately adopt in respect to Stablecoins and how these function alongside the goals and objectives of Central Bankers.

Q. Is 2022 going to be the year that we finally see mass adoption of digital market infrastructure?

I believe it is somewhat naive to expect mass adoption of a fully digitised market infrastructure as some sort of big bang event.  As we are well aware, market evolution is predicated upon extensive, iterative analysis relative to, amongst others, the technological, operational, regulatory, financial and human resource implications of changes to the broader infrastructures upon which daily market interactions reside.  I expect to see a greater embrace of digitised infrastructures by large global market participants in 2022, but this will be a gradual process, and I expect to see this enhanced participation as the primary catalyst for progress on the regulatory front.