How do you defend against identity fraud?

AZN Antifraud Suite helps financial institutions to mitigate challenges associated with meeting KYC, AML and CFT compliance during digital client onboarding process.

In North America and Europe, if a customer cannot be verified during the initial account creation process through Electronic Identification Verification (e-IDV), clients are requested to upload valid ID documents online or through a mobile device (selfie) and perform ID document verification. In some cases, ID document upload is not even required to complete digital onboarding and allow clients access to financial instruments.

Most solutions on the market today limit their capabilities to using facial recognition to evaluate uploaded documents for visual manipulations and determine the likelihood that the faces on those documents belong to the same person.

However, such approach is helpless against identity fraud. In this case, fraudsters have access to genuine ID documents, photos, and personal information including social media profiles. Even human operators can not detect this attack vector since provided documents are valid and the documents ownership cannot be ascertained.

Last line of defense against identity fraud

In countries where the e-IDV process is readily available for digital onboarding process integration, behavioral analytics has become the last line of defense against risks associated with rising identity theft-based fraud vectors, image morphing and sophisticated neural networks powered image editing tools.

In regions where e-IDV process is limited, or not available at all (e.g. Sub-Saharan Africa), meeting KYC, AML and CFT requirements can only be attained with a human review during digital onboarding. However, in the event of stolen identity, human review is powerless and behavioral analytics becomes the only line of defense available to a business.

AZN KYC Platform includes these identity proofing services:

  • Address Services: Validate and corroborate the user’s address with independent, third-party sources.

  • Identity Verification: Automated and hybrid solutions for identity proofing that deliver the industry’s highest level of verification accuracy.

  • Biometrics: Advanced liveness detection and face matching technologies for unsurpassed identity assurance and ease of use.

  • Fraud: Dramatically reduce new account fraud with anomaly detection, blocklist checks and a required selfie.

  • Databases: Automated database pings, including government watchlists, DMV and PEPS and sanctions help identify fraud and AML risks faster.

  • VIDV - Live/Ondemand: video and voice verification/re-authentications. Match provided ID documents with live/recorded video. Video stream active scanning.

  • Authentication and AML Monitoring: AZN offers a number of services designed to safeguard and empower compliance teams mitigate the threat of money laundering and other financial crimes.

360 Degree Onboarding Fraud Protection

Step 4
Data consistency

Compare computer vision data extracted from ID documents with data provided on application

Step 3
Personal Identification

Match an individual to people stored in your private repository. Determine if such visual identification was used in prior onboarding and view applications.

Step 2
Face Verification

Compare the likelihood that two faces belong to the same person; such as selfie and uploaded ID document based on confidence score.

Step 1
Facial recognition

Photo upload or selfie. Detect one or more human faces along with attributes such as age, emotion, gender, pose, smile, and facial hair. Size and metadata analysis

Step 5
MRZ Checksum validation

Machine Readable Zone (MRZ) code to identify a document's holder, as well as assess its validity and detect tampering with checksum warning visual intensifiers.

Step 6
Digital Forgery Detection

Detecting counterfeit identity documents by examining special fonts, with the applicability of convolutional neural networks (CNNs)

Step 7
Digital footprint analysis

Applicant's online reputation score determination.

Step 8
Behavioral analytics

500+ data points. Proprietary ML semi-supervised neural networks constantly evolve to attain better accuracy.

Autonomous Defense technology

Our solution relies on AI-powered User Behavior Analytics (UBA) and known fraud metrics. UBA is based on the premise that human beings have distinct patterns of behavior, and identifying any deviations in these patterns can point to criminal intent.

The combination of AZN Fraud score and ID Document Verification during the Customer Due Diligence check assists financial institutions in meeting Anti-Money Laundering (AML), Know Your Customer (KYC) and Counter Terrorist Financing (CTF) compliance requirements, as well as reducing the risk of fraud. Our solution also assists with determination if data provided during the onboarding process crosses the threshold for Ultimate Beneficial Owners (UBO) reporting. Our country-specific, configurable antifraud metrics allows our clients to set requirements for each country they operate in:

  • Simplified Due Diligence (“SDD”)

  • Basic Customer Due Diligence (“CDD”)

  • Enhanced Due Diligence (“EDD”)

AZN Antifraud collected additional information for higher-risk customers provides a deeper understanding of customer activity to mitigate associated risks. In the end, while some EDD factors are specifically enshrined in a country’s legislation, it’s up to a financial institution to determine their risk and take measures to ensure that their customers are not bad actors.

Digital ID Verification and Forgery Detection Process

  • Facial recognition
  • Face verification
  • Personal identification
  • MRZ validation
  • ID Document consistency
  • Digital and Physical tampering detection
  • Digital Footprint

Detect one or more human faces along with attributes such as age, emotion, gender, pose, smile, and facial hair, including 27 landmarks for each face in the image.

 

Compare the likelihood that two faces belong to the same person; such as selfie and uploaded ID document based on confidence score.

 

Match an individual to up to 1 million people stored in your private repository.

 

Machine Readable Zone (MRZ) code to identify a document’s holder, as well as assess its validity and detect tampering with checksum warning visual intensifiers.

 

Indicates the ‘data consistency’ section, with warning flags next to the inconsistent information.

 

Optical font recognition and its manipulation detection for ID forgery detection

Evaluation and fraud assessment of Digital footprint (digital shadow) the unique set of traceable digital activities, actions, contributions and communications manifested on the Internet or on digital devices such as social media.

 

Fraudsters use the path of least resistance to commit fraud and test exploits en masse. Millions of identities are trafficked through black markets and used to create fake accounts. In absence of e-IDV and KBA in Sub-Saharan Africa, hit rate yields a much more lucrative return on stolen identity information, than in Europe or North America. Because AZN Antifraud threshold score is based on 500 + data points and requires possession of a device in addition to compromised identity information, black market identity information isn’t sufficient to pass AZN verification.

When e-IDV process becomes available in the client’ country, it is easily integrated into AZN Antifraud Suite to further strengthen solution capabilities in preventing financial fraud by complying with KYC, AML and CFT requirements.

Contact us

 

 

By clicking this button you agree to the privacy policy.

SEND

Callback request

We will call you back within an hour or at a convenient time for you

Let's do this together -
Your business has a story

Start Project

Callback request

We will call you back within an hour or at a convenient time for you

Live Chat
×
We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.
Privacy policy