Prevent Superannuation Fraud with Voice Biometrics

MEDIA

Auraya Blog

How Voice Biometrics Can Help Prevent Further Superannuation Fraud

Angelo Gajo | May 15, 2020 | 4 minutes

ato-superannuation-fraud-activity-voice-biometrics-afp

To help alleviate the economic impact of COVID-19, many countries have implemented extraordinary assistance schemes to provide support to financially affected individuals. In Australia, the federal government approved the early release of personal superannuation of up to AUD 10,000 until June 30 and a further AUD 10,000 from July 1 to September 24 as one of the assistance measures. Whilst this early release program can greatly assist those who are in financial struggles, it also opened new opportunities for fraudsters to take advantage of the situation.

The reports of fraudulent activities regarding this scheme provided details of how fraudsters stole money from others via account takeover attacks. Using stolen personal information, fraudsters were able to steal money by accessing the victims’ superannuation funds. The Australian Taxation Office (ATO) and the Australian Federal Police (AFP) are currently investigating this incident. The AFP has stated that they were investigating up to 150 potential victims and have executed five search warrants and frozen several bank accounts. 

The ATO quickly suspended the scheme and later reopened applications for the scheme after implementing stronger end-to-end security. One security method the ATO could have implemented when the scheme was first implemented was requiring a voice biometric verification as one of the risk filters. With Auraya’s voice biometric technology, the ATO could have required people who were applying to verify their identity and enrol their voiceprint when submitting their applications. This process would have enabled the ATO to voice match each applicant against the other applicants to ensure that the same voice wasn’t being used for multiple identities.

Auraya’s voice biometric technology can be implemented in contact centres, web browsers and mobile applications, allowing the users to submit applications securely and seamlessly on any platform. This frictionless method can also be added as a part of a multi-factor authentication approach to further improve security. 

With Auraya’s voice biometric technology, organisations can make it harder for fraudsters who already possess stolen personal information from perpetuating scams. Auraya’s voice biometric technology can also detect electronically generated and recorded playback voices. Once a fraudster has provided a voiceprint then that fraudster can be detected every time they reappear trying another scam.

MORE


passwords-list-insecure-duplicate-voice-biometric

Blog

Secure Password Resets with Voice Biometrics

17 June 2020

identity-theft-fraud-voice-biometrics-scam

Blog

Protect Against Identity Theft with Voice Biometrics

27 May 2020

covid-19-report-biometrics-institute-response-paper

Blog

Biometrics Solutions and Concepts for COVID-19

20 May 2020

NEWSLETTER

sign up to our mailing list


Subscribe

What Sets Auraya's ArmorVox Engine Apart

MEDIA

Auraya Blog

What Sets Auraya’s Next-Gen Voice Biometric ArmorVox Engine Apart

Angelo Gajo | March 4, 2020 | 6 minutes

woman-voice-biometrics-smart-phone-authentication-next-gen-armorvox

Telcos and large banks were the first industries to implement voice biometrics to improve security in large contact centres. Now that voice biometric technology is proven to improve security, privacy and customer experience, other industries are integrating voice biometrics into their systems to provide improved customer experience and the efficiency benefits of automating customer verification. Despite the growth in voice biometric adoption, there are still some common concerns (or misconceptions) people have regarding voice biometrics.

In a Live Mint blog, the author discussed how beneficial voice biometrics is as it analyses hundreds of voice characteristics and traits to seamlessly verify a person’s identity. This article also points out issues regarding reliability and security. The author addresses two major concerns: voiceprint quality and the potential to spoof a voiceprint using fraudulent replication and recording of the real customer’s voice. In another blog, the author notes issues relating to data privacy and rigid customer experience. Fortunately, with Auraya’s next-gen ArmorVox voice biometrics technology, these concerns have been addressed to ensure that both organisations that deploy Auraya’s voice biometric solutions and their customers are satisfied with the security of their personal data, the reliability of the identification and most importantly the improvement in customer experience during the verification process.

When enrolling a voiceprint or verifying a person’s identity, advanced machine learning algorithms ensure enough high-quality audio is collected for the enrolment and the verification process. With ArmorVox, the audio is examined and extraneous noise is eliminated to ensure its quality is acceptable. No poorly recorded voiceprints are enrolled. ArmorVox uses advanced machine learning algorithms to detect the speaker’s voice apart from other noises and determine if the volume or quality of the voice is acceptable.  

While using advanced machine learning algorithms to ensure high-quality audio is obtained, ArmorVox also includes a fraud detection capability to detect and reject various spoof attempts. This capability can detect and reject attempts such as synthetic and recorded voice attacks. This means fraudsters can’t simply recreate someone’s voice synthetically or even directly record their voice and expect to successfully break into the system. To further prevent repeat offenders from continuously attempting to break into the system, organisations can add the voiceprints of offenders into an Impostor List. With an Impostor List, organisations can track when fraudsters attempt to break into the system and block them, all in real-time.

But what sets ArmorVox apart from standard voice biometric technologies is how it obtains and handles customers’ data. The database that stores the encrypted voiceprints is always under the direct control of the organisation that is responsible for maintaining the privacy and integrity of their customers’ data. This means no customer data is shared with service providers or third-party organisations including Auraya. ArmorVox provides organisations with the power to manage the security and privacy of their customers’ data. No data ever needs to leave the secure data repository for any purpose. This gives organisations better security and drastically reduces the chances of organisations being targeted and exposing sensitive information to fraudsters.

It’s imperative to ensure that the whole process, from enrolment to authentication, provides a delightful experience to customers. ArmorVox enables this by allowing organisations to use various voiceprint tokens such as text-dependent, text-independent, text-prompted or digit-independent voiceprints. This allows organisations to implement the best possible experience for customers whether they prefer verifying their identity by stating their customer account number or phone number or by simply conversing with an agent or a chatbot.

As voice biometrics becomes a more ‘mainstream’ user interface, the list of concerns is reducing. Auraya’s next-gen voice biometric technology does an excellent job in addressing all the common concerns of voiceprint quality, security performance, spoof protection, data privacy and customer experience. That’s what makes ArmorVox the next generation of voice biometric technology.

MORE


passwords-list-insecure-duplicate-voice-biometric

Blog

Secure Password Resets with Voice Biometrics

17 June 2020

identity-theft-fraud-voice-biometrics-scam

Blog

Protect Against Identity Theft with Voice Biometrics

27 May 2020

covid-19-report-biometrics-institute-response-paper

Blog

Biometrics Solutions and Concepts for COVID-19

20 May 2020

NEWSLETTER

sign up to our mailing list


Subscribe

Goode Intelligence Interviews CTO Dr. Clive Summerfield

MEDIA

Auraya Blog

Goode Intelligence Interviews CTO Dr. Clive Summerfield

Angelo Gajo | February 19, 2020 | 4 minutes

biometric-summit-london-2019-clive-summerfield-interview

Goode Intelligence interviewed our CTO and co-founder, Dr. Clive Summerfield December last year for the Biometric Summit 2019 event in London. The interview covered the present challenges of biometric technology and its potential benefits to customer experience and security. Most importantly, it focused on the capabilities of voice biometrics and how it can seamlessly achieve delightful customer experience and bolster security. Below is the transcript for the interview between Goode Intelligence (GI) and Dr. Clive Summerfield (CS). You can check out the official published interview here.

GI: What challenges are organisations facing today that you feel biometrics can help to solve?

CS: Biometrics – specifically voice biometrics – solve not just the burgeoning fraud problem, but many of the compliance issues relating to the delivery of secure online and telephony customer service.

GI: How do you feel biometric technology can enhance customer experience to deliver great customer service for end-users?

CS: Voice biometrics makes identity authentication seamless and invisible to the customer. No passwords to remember, no PINs to forget.

GI: How are you expecting to see the industry change or evolve over the next 12 months?

CS: We expect to see voice become the defacto second-factor authentication credential for online banking, financial services and access to cloudbased services.

GI: Where are you seeing the greatest demand for biometrics?

CS: The greatest demand at the moment is in the traditional password reset. Looking forward, it is just a small step from password reset to secondfactor authentication and password replacement.

GI: What do you feel the most exciting innovation is for biometric technology at the moment?

CS: Biometric in the browser! With the emergence of HTML5, it is now possible to insert voice biometrics into website and WebApps in no time at all, providing a convenient way to deliver biometric security across a wide range of markets and applications.

GI: How can new technologies and regulations support authentication and satisfy the greater demand for security and trust?

CS: Regulation, such as GDPR and PSD2, is at the heart of building trust and confidence in the technology and ensuring the responsible and ethical application of this powerful technology.

GI: What would you advise to those looking to deploy biometric technology in their organisation to consider?

CS: Start with the customer experience and work back from there.

MORE


passwords-list-insecure-duplicate-voice-biometric

Blog

Secure Password Resets with Voice Biometrics

17 June 2020

identity-theft-fraud-voice-biometrics-scam

Blog

Protect Against Identity Theft with Voice Biometrics

27 May 2020

covid-19-report-biometrics-institute-response-paper

Blog

Biometrics Solutions and Concepts for COVID-19

20 May 2020

NEWSLETTER

sign up to our mailing list


Subscribe

Active Versus Passive Verification

MEDIA

Auraya Blog

Active Versus Passive Verification

Angelo Gajo | February 13, 2020 | 4 minutes

active-passive-authentication-voice-biometrics-versus

Using voice biometrics to identify or verify someone provides a seamless and delightful customer experience. Voice biometrics replace traditional and outdated security methods such as PINs, passwords and answers to security questions, offering a more secure and friction-free method to verify identity in telephone calls and digital transactions.

With EVA, Auraya’s voice biometric extension for Amazon Connect, organizations can take advantage of both active and passive verifications. EVA allows companies to take advantage of text-dependent, text-independent, text-prompted or digit-independent voiceprints to provide active and passive verification processes in all channels. Both provides delightful user experience and performance benefits, so it’s important to have both options available to ensure your voice biometric solution provides the best outcomes for customers and organizations in all scenarios.

Active verification is when a speaker is asked to say a specific phrase or simply say their account number or phone number to be verified. This type of verification allows a customer to be verified by a self-service bot so they can take advantage of self-service options that are appropriate for customers whose identity has been verified. This method also allows customers to be verified in digital channels or when using chatbot or a mobile application or when they are using a web browser to complete a secure transaction.

Passive verification involves listening to the speaker’s voice whilst they are talking with an agent or a voicebot. This process normally requires a longer period of speech to achieve a high-security verification score. Passive verification means a caller doesn’t need to remember their account number or phone number which is a benefit for some customers. Some customers may have some security concerns if they think the call center agent hasn’t asked for any proof of identity and just completes their transaction without consideration to the security of the account holder.

Both passive and active voiceprints can be enrolled from agent conversations or historical call records if appropriate compression settings on the recordings are maintained. Some jurisdictions also require specific alerts to request permission to use the recordings for voice verification purposes.

Active verification requires less speech and it usually only takes 2-3 seconds of speech for high-security verification. Passive verification can be advantageous as it allows users to be verified whilst in conversation with an agent. Passive verification is also useful for fraud detection purposes as it allows companies to continually monitor conversations in real-time to ensure that the person they are interacting with is still the authenticated speaker.

Both active and passive voice verification provide different benefits depending on the use case. The ability to use both active and passive ensures that organizations and their consumers will get the best outcome from a voice biometric solution.

MORE


passwords-list-insecure-duplicate-voice-biometric

Blog

Secure Password Resets with Voice Biometrics

17 June 2020

identity-theft-fraud-voice-biometrics-scam

Blog

Protect Against Identity Theft with Voice Biometrics

27 May 2020

covid-19-report-biometrics-institute-response-paper

Blog

Biometrics Solutions and Concepts for COVID-19

20 May 2020

NEWSLETTER

sign up to our mailing list


Subscribe

How 2019 Fared with Data Breaches

MEDIA

Auraya Blog

How 2019 Fared with Data Breaches

Angelo Gajo | February 6, 2020 | 4 minutes

data-breach-cyber-crime-attack-access

Identity Theft Resource Center has released its ‘End-of-Year Data Breach Report’ for 2019, giving us new insights on the severity and magnitude of data breaches compared to 2018. In this report, Identity Theft Resource Center found that the total number of data breaches reported in 2019 increased by approximately 17% since 2018. However, surprisingly, the number of overall records exposed in 2019 dropped by approximately 50% compared to 2018. This finding reflected in the number of personally identifiable information (PII) exposed, where it decreased by 41% since 2018. These results may be largely due to the fact that organisations are starting to implement more robust and rigorous security methods, amidst the growing threats of cyber-attacks. Some of these methods include biometric authentication such as voice, facial, and fingerprint authentication.

The report focused on five major industries of Business, Medical/Healthcare, Education, Banking/Credit/Financial and Government/Military. Out of the five, the Business industry experienced the most data breaches as it accounted for 43.7% of the total data breaches in 2019. The Medical/Healthcare industry comes in second at 35.6% while the Banking/Credit/Financial industry is only at 7.33%. However, the Banking/Credit/Financial industry actually exposed the greatest number of sensitive records, accounting for 61.1% of the total number of sensitive records exposed in 2019. Gaining access to sensitive records can leave millions of people vulnerable. PPI data such as full name, date of birth, place of address is enough for hackers to perform account takeovers or identity theft. If implemented, organisations with updated and high-level security methods, such as voice authentication for services like authorisation and account access, can not only prevent cybercriminals from successfully breaking in, but it can also deter others from trying.

The most interesting finding in the report is that unauthorized access was the second most common method, accounting for 36.5% of the total data breaches. The most common method was hacking/intrusion at 39%. Although only second, unauthorized access was actually responsible for 86% of the exposed sensitive records. People with weak or obvious security settings such as guessable passwords or insecure account logins are easily exposed by unauthorized access attempts. Additionally, cybercriminals can easily outwit traditional security methods such as passwords, PINs and even email security codes. By infiltrating sensitive records, cybercriminals can obtain more information which is then used to assist in more unauthorized access. However, with voice biometrics such as Auraya’s EVA voice biometrics extension for Amazon Connect, user identification and verification can be made simpler and provide a frictionless user experience. EVA allows organisations to implement key voice biometric capabilities such as identification & verification and fraud detection to their existing system solutions to improve overall security. With EVA, organisations can implement voice biometrics in any language and in any channel, whether it is through a contact centre, a mobile app, a chatbot or an HTML5 webpage. EVA cannot be mimicked, recorded or synthesized and can detect and flag fraudulent attempts in real-time. Cybercriminals attempting to gain unauthorized access to accounts will struggle to succeed as their voice or any voice other than the original account owner continues to fail again and again.

MORE


passwords-list-insecure-duplicate-voice-biometric

Blog

Secure Password Resets with Voice Biometrics

17 June 2020

identity-theft-fraud-voice-biometrics-scam

Blog

Protect Against Identity Theft with Voice Biometrics

27 May 2020

covid-19-report-biometrics-institute-response-paper

Blog

Biometrics Solutions and Concepts for COVID-19

20 May 2020

NEWSLETTER

sign up to our mailing list


Subscribe

Amazon Connect Now Available in APAC AWS Region

MEDIA

Auraya Blog

Amazon Connect Now Available in Asia-Pacific AWS Region

Angelo Gajo | January 15, 2020 | 3 minutes

auraya-amazon-connect-aws-singapore

On December 19 last year AWS announced that their cloud contact center service Amazon Connect was finally available in the Asia-Pacific (Singapore) AWS region, bringing the total number to seven global AWS regions. With this expansion, organisations in the Asia-Pacific region are now provided with more options to provision their Amazon Connect cloud contact center. 

One of these options includes Auraya’s EVA voice biometrics extension for Amazon Connect. EVA is a ready-to-use, cloud-based voice biometric extension for telephony and digital channels. Designed for seamless integrations, EVA provides organisations with voice identification & verification capabilities in their Amazon Connect platform. Additionally, organisations can implement EVA fraud detection capabilities to ensure that their customers are protected from fraudulent attempts such as Account Takeovers.

EVA allows organisations to reduce agent-handling costs and ensure stronger security from fraudsters while providing a frictionless and delightful customer experience.

To celebrate the occasion, Auraya was invited to Singapore last week by the AWS team. Auraya’s managing director Ray Doak and CEO Paul Magee was in attendance and presented EVA voice biometric extension for Amazon Connect to the crowd. If you’re interested in learning more about EVA and how it can benefit your organisation, don’t hesitate to connect with Auraya at info@aurayasystems.com.

About Amazon Connect

Amazon Connect is a cloud-based contact center where organisations can manage inbound and outbound customer interactions over various channels such as telephony, web, chat and emails. Amazon Connect provides a seamless experience across voice and chats for customers and agents through the use of routing tools, management tools and analytics. Amazon Connect helps improve agent efficiency and lower costs, saving more time for an organisation’s customers.

About Auraya

Auraya is a world leader in voice biometric technology with the mission of empowering people and organisations to interact and engage with convenience and security in all channels and languages. Designed for telephony and digital channels, ArmorVox is Auraya’s next-generation voice biometric engine capable of voice identification & verification and fraud detection. The EVA extension for Amazon Connect is powered by the ArmorVox engine, ensuring organisations with a seamless and frictionless customer experience and enhanced security.

MORE


passwords-list-insecure-duplicate-voice-biometric

Blog

Secure Password Resets with Voice Biometrics

17 June 2020

identity-theft-fraud-voice-biometrics-scam

Blog

Protect Against Identity Theft with Voice Biometrics

27 May 2020

covid-19-report-biometrics-institute-response-paper

Blog

Biometrics Solutions and Concepts for COVID-19

20 May 2020

NEWSLETTER

sign up to our mailing list


Subscribe

Integrating Voice Biometrics in the Healthcare Industry

MEDIA

Auraya Blog

Integrating Voice Biometrics in the Healthcare Industry

Angelo Gajo | January 9, 2020 | 4 minutes

healthcare-industry-services-devices-telephony-digital-voice-biometrics

Over recent years, the healthcare industry has been moving away from traditional paper-based medical records and resources towards a more electronic-based system of record. Electronic health records (EHR) means that health professionals and patients have 24/7 access to accurate and updated information. Health professionals can seamlessly bring up medical records and make quicker and more precise assessments while patients can access their collective medical records all in one place at any time.

Exposed to Threats

However, amidst all these benefits lie some concerns. Medical records are private and require authorised personnel access. Gaining access often involves traditional and laborious methods such as obtaining SMS tokens and one-time pins, forcing the user to juggle between devices or between apps. Additionally, by digitalising sensitive and private medical records, patients become vulnerable to cybersecurity threats. There are many ways cybercriminals can breach healthcare data. For example, criminals who have access to the patient’s devices or know the patient’s security answers can easily access their accounts. Further, compromised passwords can leave patients’ accounts and their medical records vulnerable. 

Voice Biometrics

Fortunately, with voice biometrics, healthcare organisations can protect both their medical staff and patients. Unlike fingerprint and facial recognition, voice biometrics can be used on any device with a microphone such as a tablet, PC, or a medical device like an x-ray machine. To gain access to records and other resources, users simply need to use their voice to verify their identity. With Auraya’s EVA voice biometrics technology, healthcare organisations can implement voice biometrics in any channel, whether it’s telephony or digital channels. Through machine learning algorithms and various patented features, EVA can continually improve users’ voiceprints to ensure accurate and secure verification performance over time. With real-time fraud detection and prevention, EVA can flag and deflect any unauthorised access. Organisations can build impostor lists to track and block fraudsters. Any fraudster aiming to break through using synthetic voices, whether it’s been recorded, mimicked or generated, will also be detected and blocked.

Use Cases

Voice biometrics can be integrated in various use cases in the healthcare industry. Voice biometrics can be used to log into online portals where medical records are stored ensuring delightful customer experience and enhanced security. Voice biometrics can also be used in online password reset services to ensure efficient and secure password resets, saving medical staff and patents precious time. Another valuable use case is the identification and verification of patients during customer interactions in call centres. If enrolled, call centre agents can easily identify or verify callers with voice biometrics. This allows agents to quickly provide a service or access required information regarding the caller, saving precious time – especially in an event of an emergency. Other simple implementations could involve implementing voice biometrics into digital kiosks, allowing customers to be identified when obtaining a service through a voice-assistant enabled kiosk. 

MORE


passwords-list-insecure-duplicate-voice-biometric

Blog

Secure Password Resets with Voice Biometrics

17 June 2020

identity-theft-fraud-voice-biometrics-scam

Blog

Protect Against Identity Theft with Voice Biometrics

27 May 2020

covid-19-report-biometrics-institute-response-paper

Blog

Biometrics Solutions and Concepts for COVID-19

20 May 2020

NEWSLETTER

sign up to our mailing list


Subscribe

Achieve Accurate and Efficient Security Performance

MEDIA

Auraya Blog

How ArmorVox Achieves Accurate and Efficient Security Performance

Angelo Gajo | January 8, 2020 | 6 minutes

process-automation-security-settings-machine-learning

Integrating voice biometric capabilities into any business solution should be easy and hassle-free. However, security managers often spend countless hours tuning the settings and thresholds to obtain optimal security performance. Opting for a system-wide security setting can pose security issues as each speaker will have different levels of security, resulting in ineffective security performance. Auraya’s next-gen ArmorVox voice biometric engine and its patented features, allows organisations to easily deploy voice biometrics seamlessly and quickly. ArmorVox uses machine learning to optimise the security performance of every individual voiceprint automatically. Security managers can be assured of having the best security performance from day one of deployment with continuous optimisation for every user every time they use the system.

Automated Tuning of Background Models

ArmorVox uses a patented process of creating a speaker-specific background model for every voice print enrolled in a system. A speaker-specific background model means users can speak in their preferred language and achieve optimal performance from a security perspective and in terms of user experience. A speaker specific-background model ensures that each person enrolled has the maximum protection from attacks by people who closely resemble their voice such as a twin.

Automated Setting of Speaker-Specific Security Threshold

With ArmorVox, the security thresholds of each voiceprint are automatically calibrated using machine learning to create speaker-specific security thresholds. By calibrating each speaker’s security threshold levels, organisations can ensure a consistent level of security for every individual in the system. This means that organisations can truly achieve their desired False-Accept Rate (FAR) targets and satisfy any security requirements.

ArmorVox provides tools to allow security managers to simulate a massive hack attack where lots of enrolled users can be used to attack lots of other enrolled users. Using built-in tools to audit system performance, organisations can rest assured that their security is being constantly maintained at specified levels. The audit tools allow security managers to certify that the security thresholds that are nominated for different types of transactions are in fact being delivered by the solution.

MORE


passwords-list-insecure-duplicate-voice-biometric

Blog

Secure Password Resets with Voice Biometrics

17 June 2020

identity-theft-fraud-voice-biometrics-scam

Blog

Protect Against Identity Theft with Voice Biometrics

27 May 2020

covid-19-report-biometrics-institute-response-paper

Blog

Biometrics Solutions and Concepts for COVID-19

20 May 2020

NEWSLETTER

sign up to our mailing list


Subscribe

How to Get an Identity Claim in a Frictionless Voice Biometric Verification Process

MEDIA

Auraya Blog

How to Get an Identity Claim in A Frictionless Voice Biometric Verification Process

Paul Magee | December 11, 2019 | 6 minutes

lady-phone-accounts-number-login-identifier

Biometric voice verification works best when a ‘one-to-one’ match is requested. One-to-many verification processes can lead to poor security or usability outcomes. To verify based on a ‘one-to-one’ or ‘one-to-few’ comparison the claimed identity of the caller needs to be established. The following options can be used to make this process seamless for any user, therefore, delivering on the promise of frictionless customer experience.

      1. Using information from the device that is being used by the person such as the Automatic Number Identification (ANI, or sometimes referred to as CLI) can be a proxy for one or more possible customers, so allowing the system to collect the calling line identifier and doing a database check to see if that ANI has a corresponding customer(s) record is the first step in addressing the identification process.
      2. As ANI may not always identify the caller and customers may interact on multiple devices ANI cannot be relied on as the only identification element so asking a customer to say their account number or phone number provides another input to determine the claimed identity. This spoken utterance helps refine the claimed identity as it may be the same as an ANI or a different number.
      3. Some customers may already have been trained to input their account number or phone number using DTMF (push buttons on the phone). Whilst it is preferable not to have a system that requires speech input and DTMF tones we can use the DTMF tones to establish claimed identity and then ask the caller to say their account number or phone number to do the biometric verification.
      4. Claimed identity can also be inferred when using push to talk or other digital devices or in outbound calls based on the device identity.
      5. If the customer is interacting with a bot or agent via a digital device then the device identifier (IP address, browser cookie, keyboard input, etc) can be used to determine the claimed ID.
      6. Some organisations have an existing speech recognition system that asks for name and address or other identifiers that narrow the list of potential customers. This is not a recommended process as it often doesn’t deliver the frictionless experience nor the necessary accuracy to deliver a delightful experience. Maintaining a speech recognition system to accurately recognise names is expensive, however, if an organisation already has this functionality it can be leveraged to determine claimed identity.
      7. Other techniques are depending on the user group and geography to narrow the potential candidate identities for example in the UK saying a postcode will narrow the range of potential candidates to a small number.

Once all relevant techniques have been used to narrow the probable candidates to ‘one’ or a ‘few’ potential candidates the speech sample that was collected by the initial identification question (phone number or account number or postcode, etc) can be compared against either the one candidate or the few alternative candidates. If there is only one match, then this provides the answer to the question of who is calling, and they have been verified to a sufficient level of assuredness to continue the seamless friction-free journey.

All these options are available as well as others that can be used in different use cases. Any of these variants can be incorporated into the EVA solution by customising the solution using Amazon Connect‘s orchestration tools.

It is important to note that most interactions are resolved with two inputs:

      1. ANI and;
      2. Saying your phone number (or account number, or either) and resolve the identity question and verification question with one utterance.

For solutions focused on internal staff where one ANI may resolve to hundreds or more staff members then we normally recommend asking the caller “to verify your identity, please say your phone number” as most employees have a mobile phone number that they say easily then this number becomes their claimed ID and verification utterance. Of course, you could replace phone numbers with employee numbers but often employees don’t remember or aren’t able to say their employee numbers.

MORE


passwords-list-insecure-duplicate-voice-biometric

Blog

Secure Password Resets with Voice Biometrics

17 June 2020

identity-theft-fraud-voice-biometrics-scam

Blog

Protect Against Identity Theft with Voice Biometrics

27 May 2020

covid-19-report-biometrics-institute-response-paper

Blog

Biometrics Solutions and Concepts for COVID-19

20 May 2020

NEWSLETTER

sign up to our mailing list


Subscribe

One Way the Commonwealth Bank Can Protect Itself from a Major Phishing Scam

MEDIA

Auraya Blog

One Way the Commonwealth Bank Can Protect Itself from a Major Phishing Scam

Angelo Gajo | December 5, 2019 | 5 minutes

phishing-email-scam-commbank-mailguard

The Commonwealth Bank is an Australian multinational bank offering personal and business banking services and solutions to its customers. On November 29, a phishing email posing as Commonwealth Bank was detected by MailGuard. The phishing email requests the recipients to verify their transaction details and activity through a hyperlink. Upon clicking the hyperlink, the recipients are directed to a fake login webpage under the fake domain Commbonk where customers are asked to log in using their client number and password. Once entered, the customer’s details are then harvested by the cybercriminals. The appearance of the fake login webpage is very similar to the original Commonwealth Bank webpage, with the only difference being the URL. With webpage designs being easily copied and replicated, this method of phishing for customer data is easy to attempt for fraudsters and hard to detect by legitimate customers.

commbonk-login-portal
commbank-login-portal

The Similarities Between CommBonk and CommBank’s Login portals (Source: MailGuard)

Companies like Commonwealth Bank can improve their digital security posture and deter phishing attempts by replacing traditional security methods such as PINs and passwords with Auraya’s voice biometric technology. Not only will this improve security for banks’ online services, but it will also provide a delightful and seamless customer experience. With voice biometrics, customers will be required to click on a microphone icon to activate their device’s microphone and speak a random series of digits that are displayed on the screen to verify their identity.

With voice biometrics, customers no longer need to remember passwords or secret answers or reveal their sensitive information such as date of births, addresses and other personally identifiable information to verify their identity whether it is on a browser webpage, digital app, or to an actual agent in a call centre.

Voice biometrics login make phishing for your password and PIN’s worthless. Fraudsters could try to capture a recording of you saying your ‘one-time voice code’ however this won’t help as every login requires a different random digit which is easy for the legitimate customer to say and impossible for the fraudster.

What sets apart Auraya’s voice biometrics technology from PINs and passwords is that voice biometrics cannot be mimicked, recorded or synthesized. Through Auraya’s patented features, Auraya’s ArmorVox voice biometric engine can detect and flag fraud attempts made with recorded, mimicked or synthesized voices. Random challenges render pre-recorded voices useless. This means that customers who are fooled by phishing emails and fake login portals would still be safe and secured from fraudulent attempts made against their accounts.

MORE


passwords-list-insecure-duplicate-voice-biometric

Blog

Secure Password Resets with Voice

17 June 2020

identity-theft-fraud-voice-biometrics-scam

Blog

Protect Against Identity Theft with

27 May 2020

covid-19-report-biometrics-institute-response-paper

Blog

Biometrics Solutions and Concepts for

20 May 2020

NEWSLETTER

sign up to our mailing list


Subscribe

1 2 3 8