
Resistant AI
Resistant AI protects the automation and AI systems of financial services from manipulation and attack. It subjects every customer interaction — from documents submitted at onboarding to ongoing behaviors — to forensic analysis to detect document forgery, serial fraud, synthetic identities, bots, account takeovers, money laundering, and unknown financial threats operating at scale.
Fraud Solution Profile
Software is eating the world — and financial crime is no exception. Criminals are iterating at the speed of startups, finding new weaknesses in the AI and automations of financial services, and using automation of their own to exploit them at scale. The only way to tackle these unknown, emergent threats is to submit every single customer interaction to a level of scrutiny previously only available to human review — but at scale and economically thanks to AI techniques.
Resistant AI’s Identity Forensics provides that scrutiny by layering on top of existing customer systems. It uses data from across the entire customer journey, augmenting (rather than replacing) all existing tools and the human teams who use them with truly smart AI that protects them from manipulation and attack.
As such, it has a whole range of applications in financial services, including:
- Onboarding/KYC/KYB
- Claims analysis
- Transactional fraud prevention
- Anti-Money Laundering
- And applications for a whole host of lending models, from consumer mortgages to point-of-sale lending like Buy Now Pay Later
Identity Forensics has 5 modular capabilities that can be deployed independently and in any configuration as needed:
Document forgery detection
Each PDF or image submitted as part of Onboarding/KYC, loan applications or insurance claims gets analyzed over 500 different ways to catch signs of forgery — even on documents never seen before.
Serial forgery detection:
All documents are compared to detect forgery patterns, uncover common templates behind industrially produced forgeries, and highlight identity reuse across different services.
Serial onboarding detection
Any available behavioral data — from device intelligence to service usage patterns and more— is used to detect bulk account creations, stolen identities, bots, and account takeovers.
Behavioral analysis
Every customer transaction gets analyzed in context for transaction fraud and financial crimes like layering, smurfing, cycling and any other sign of as-yet-undefined malicious behavior.
Identity Clustering
Fuses all that knowledge to uncover controlling entities behind multiple accounts, dismantle whole organized crime rings and robotic money mule networks, and identify account takeovers before they have time to commit damage.
What you can expect from Resistant AI:
- Hunt for unknown threats before they can scale and do damage.
- Get holistic views of the entire customer journey to make your risk scoring adaptive
- Confidently get to conclusions faster with human-readable and fully justifiable verdicts that satisfy both compliance and judicial requirements.
- Make your onboarding faster and cheaper onboarding with less friction.
- Discover the links between seemingly separate suspicious identities and transactions to dismantle whole criminal rings in one go.
- Augment your existing tech stack with truly smart AI and avoid costly replacements.
- Automate the approvals and declines of applications or transactions based on tailored risk tolerances.
- Catch synthetic and stolen identities, account takeovers, bots, and more.
- Discover forgeries the human eye can’t in ID cards, account statements, payslips, invoices, utility bills and more.
- Automatically prioritized alerts focus investigators on the highest risk cases.
- Optimize underlying rules to reduce false positives and surface true risks.
- Detect advanced layering and muling techniques and other unknown behaviors.
Payoneer
Habito
Twisto
Moneta MoneyBank
PSA Finance
Ecommerce, Financial Services, Insurance
Fraud & AML Platform
Account Takeover, KYC & AML, Loyalty or Promo Abuse, New Account Fraud, Payment Fraud, Synthetic Identity Fraud
Behavioral Biometrics, Machine Learning