Fraud Detection & Transaction Risk
R

Resistant AI

Resistant AI sells document fraud detection and transaction monitoring to banks, lenders, payment companies and insurers. Founded in Prague in 2019, with offices in London and New York, it says more than 8,000 fraud and compliance analysts use its software. Payoneer, Close Brothers, Crédit Agricole, Raiffeisen Bank, Moneta Bank, Bank of Valletta, Holvi, Anna Money and Lemonade are among its customers.

Resistant Documents checks PDFs and images for forged, tampered and AI generated documents by analyzing how each file was built and comparing it with other submissions, in under 20 seconds a document. Lenders use it on bank statements, payslips and proofs of address at onboarding, underwriting and claims, and Adaptive Decisioning maps its findings to a firm's policy for approval, escalation or rejection. The company had analyzed more than 200 million documents by July 2026.

Resistant Transactions sits on top of an existing monitoring system and adds graph analysis of money flows, behavior segments and alert triage for fraud and money laundering teams, using more than 80 ready made models plus supervised models trained on the institution's own data. Experian supplies counterparty data for one configuration.

Payoneer reports 99.2% accuracy on the verdicts configured for it, with the service covering more than 82% of its document fraud decisions. Close Brothers reports a 22 times return on investment, and Anna Money halved its alerts while catching twice the fraud. Document Forensics is sold by private offer on AWS Marketplace and through Google Cloud Marketplace.

Last VerifiedNovember 20, 2026
Compare Resistant AI with other vendors
Founded
2019
Headquarters
Prague, Czech Republic
Website
resistant.ai/
Categories
fraud-and-transaction-risk, aml-kyc-financial-crime
Assessment

Capability Axes

Capability grades

15 of 15 axes rated · 11 graded A or B

AI Capability
AI Centrality
AA on AI CentralityThe artificial intelligence is the product. Remove the models and there is nothing left to sell.
Vendor Published

Models produce everything a customer buys. A library of statistical detectors judges how each PDF or image was built and compares it with other submissions to catch reuse and coordinated fraud, and supervised and unsupervised models flag suspicious transactions through graph analysis and deviations within behavior segments. The interface and APIs only deliver those verdicts and alerts to analysts and existing systems.

Autonomy and Oversight Model
AA on Autonomy and Oversight ModelWhat the system runs alone, what constrains it, and how a person checks it are all published: modes, thresholds, sampling or audit controls, and the route a case takes to human review.
Vendor Published

Adaptive Decisioning maps document checks to a firm's own policy and sends an approval, escalation or rejection downstream, and the institution decides which outcomes act automatically and which stay with analysts. Reviewers see the signals behind each flag. Payoneer routes edge cases to people, and in transaction monitoring alerts are prioritized and enriched with related parties and activity for investigators to decide.

Model Risk Management and Transparency
BB on Model Risk Management and TransparencyReal transparency mechanisms are published, such as per alert explainability, confidence scoring or split testing, without the validation package or supervisory mapping behind them.
Vendor Published

Resistant Documents returns separate outputs for quality, document class, trust and decisioning, and developers can see which detectors fired and why. Resistant Transactions adds graph techniques and behavior segments, and institutions can train supervised models on their own data. Payoneer's 99.2% measures its configured verdicts. A full validation protocol and model version history are not public.

Operational and Outcome Evidence
AA on Operational and Outcome EvidenceNamed customers with hard performance figures and enough method to test them.
Vendor Published

Payoneer's document fraud workflow reached 99.2% accuracy on the verdicts configured for it, with the service handling more than 82% of its document fraud decisions and edge cases sent to people. Close Brothers reports a 22 times return on investment, and Anna Money halved its alerts while catching twice the fraud. Habito describes faster fraud detection in mortgages and Holvi better investigation of unfamiliar transaction risks, both without figures.

AI Safety and Data Stewardship
CC on AI Safety and Data StewardshipGeneral assurances that do not answer the question this axis asks, which is whether one customer’s data trains models serving its competitors. Unbounded cross client learning stated with no boundary grades here too.
Vendor Published

Supervised transaction models can be trained on one institution's own data, while the document service keeps learning as new evidence is labeled, and the AWS listing describes support staff feeding production signals back into model development. Whether one customer's labeled fraud improves the detectors used by others is not stated. Deletion and retention policies exist but sit behind the trust center's access request.

Regulatory and Compliance
GLBA and Data Privacy Posture
BB on GLBA and Data Privacy PostureA substantive privacy document that reaches the product itself, short of the subprocessor list or the full data handling detail.
Vendor Published

Resistant Documents examines the structure of a file and can work without reading the personal data written in it. Customer data is encrypted at rest and in transit, and the trust center names cloud providers such as AWS as authorized processors bound by data protection terms. The full subprocessor list, deletion policy and retention policy are released through the trust center on request, and the public privacy notice covers website data.

Security Certifications and Trust Center
BB on Security Certifications and Trust CenterA recognized certification named in the vendor’s own material without the artifact, or with a scope or renewal question the buyer has to raise.
Vendor Published

The HyperComply trust center lists a SOC 2 Type II report and bridge letter, and a November 2026 update announced completion of the latest audit. Sensiba San Filippo audited the earlier Type II report. The reports, product security assessments and access and data handling policies are released on request, so the scope and dates of the current audit come with the document.

Regulatory Status and Licensure
BB on Regulatory Status and LicensureThe regulatory position is clearly stated and appropriate to the product, with part of the verification left to the buyer.
Vendor Published

Banks use Resistant AI inside their own know your customer, fraud and anti money laundering processes and keep responsibility for decisions, suspicious activity reporting and how each customer case ends. Evidence behind an alert stays available to analysts as they review it, and an EU AI Act position paper is available through the trust center on request.

AI Governance and Bias Disclosure
CC on AI Governance and Bias DisclosureResponsible artificial intelligence committed to in policy language with no evaluation behind it, on a product whose bias surface is modest.
Vendor Published

Transaction models run per behavior segment so expected activity in one group is not judged against another, and document checks work across file formats and languages. Both services put findings in front of a reviewer, and the EU AI Act document is available on request. No demographic test of whether flags or verdicts fall unevenly across customer groups has been released.

AI Liability and Recourse
CC on AI Liability and RecourseMechanisms that enable challenge, such as audit trails and source traceability, with nothing standing behind the output and no route for the person affected.
Vendor Published

Analysts can see the checks behind each document flag and the behavior behind each transaction alert, escalate hard cases and decide whether a finding should touch a customer. That review is the correction path. The master services agreement is released on request, and no public term offers a financial remedy for a wrong finding or a route for the affected customer.

Integration and Deployment
Model Supply Chain Disclosure
BB on Model Supply Chain DisclosureSubstantial partial disclosure, or a chain that is structurally short: an explicit in house build, on premise deployment, per customer instances, or zero retention at the model layer.
Vendor Published

The detectors behind the document service are built in house, and the transaction product ships more than 80 ready made models plus supervised models a bank trains on its own data. AWS supplies the infrastructure and Experian counterparty data for one configuration. The full subprocessor list sits behind the trust center's access request, and model versions are not named.

Core Systems and Integration Depth
BB on Core Systems and Integration DepthNamed systems or a documented public API, with the depth or the production evidence left open.
Vendor Published

Document Forensics connects through a documented API or a web interface and is available on AWS and Google Cloud marketplaces. Resistant Transactions adds alerts and prioritization on top of an institution's existing transaction monitoring system, detecting in under 100 milliseconds, and one configuration uses Experian counterparty data. Packaged connectors for particular core banking or monitoring vendors are not named.

Deployment Model and Data Residency
CC on Deployment Model and Data ResidencyCloud only with nothing stated, which is the category norm.
Vendor Published

Both services are hosted, with AWS named as the infrastructure provider and Document Forensics also offered through Google Cloud. Institutions send files and receive findings through the API inside their existing workflows. The region where a customer's documents and transactions are processed and stored is not stated and is set in each order.

Commercial
Commercial Transparency
BB on Commercial TransparencyA published plan ladder, billing dimensions, or a stated commitment such as no fees, so a buyer can size the cost before making contact.
Vendor Published

Document Forensics can be bought through a private offer on AWS Marketplace, billed through the buyer's AWS account, or through Google Cloud Marketplace, as well as directly. The current AWS listing prices on the buyer's requirements and eligibility, and Resistant Transactions is sold through demonstrations and sales. An ROI calculator stands in for a public rate card.

Institution and Segment Coverage
AA on Institution and Segment CoverageThe financial segments served are named and each carries its own maintained material, whether the coverage is broad or deliberately narrow.
Vendor Published

Banks, lenders, payment companies, insurers and marketplaces each have their own use cases. Payoneer screens documents at onboarding, Habito, LYNK Capital and Close Brothers use it in lending, Raiffeisen Bank in credit fraud prevention and Lemonade in insurance claims. Transaction monitoring serves fraud and money laundering teams at FINOM, Holvi, Anna Money and Moneta Bank, with use cases for authorized push payment fraud and buy now, pay later.

Alternatives to Resistant AI

Other products that do the same kind of work as Resistant AI, and what each one does.

T-NEX Fraud Detection is a transaction monitoring and case investigation module for fraud and anti money laundering teams at regulated institutions.

DataVisor unifies fraud detection, anti money laundering monitoring, customer and business onboarding checks, case management and risk decisioning on one platform covering the whole customer lifecycle.

NICE Actimize sells software that catches fraud and money laundering at banks and other financial institutions. Xceed puts fraud prevention, money laundering monitoring, OFAC screening and investigations on one AI platform for credit unions, community banks and smaller institutions.

SEON combines fraud prevention and anti money laundering compliance in one platform, built around enriching a thin signup input such as an email address, phone number or address into a wide risk picture.

Featurespace, a Visa solution since Visa completed its $946 million acquisition in December 2024, sells real time fraud and financial crime detection to banks, card processors, acquirers and credit unions.

Fraud.net unifies fraud prevention, anti money laundering compliance and risk management on one platform for banks, credit unions, payment processors, acquirers, remittance companies, fintechs and commerce businesses.

Commercial

Pricing

Vendor-published figures are labeled as such. Figures labeled “Estimated” are derived from third-party sources and have not been confirmed by the vendor.

Entry Price Pricing Basis Data Protection Terms Implementation Source
Quoted. AWS Marketplace pricing is by private offer.
Document Forensics is quoted on the buyer's requirements and eligibility, including through AWS Marketplace private offers. The data processing terms and subprocessor list are released through the trust center on request. Implementation fees are not listed. Marketplace purchases bill through the buyer's cloud account. Vendor Published

Document Forensics can be bought through a private offer on AWS Marketplace, billed through the customer's AWS account, or through Google Cloud Marketplace. Resistant Transactions is sold through enterprise sales. Prices for document screening and transaction monitoring are set in each offer, and an ROI calculator is available instead of a rate card.

Contact us

Found a vendor we missed? Have feedback on the index? We’d love to hear from you.

AI FinTech Index

The AI FinTech Index is an independent index that tracks changes to AI vendors in financial services. It holds 797 vendors across banking, lending, insurance, wealth, capital markets and financial crime compliance, each graded on the same 15 capability axes from public sources. No vendor pays for inclusion, placement, or rating.

Index Status
Last index update
November 21, 2026
The AI FinTech Index is an editorial reference, not a regulatory body. Vendor data is verified against published sources and public regulatory filings. Figures labeled “Estimated” have not been confirmed by the vendor. See the Methodology page for evaluation standards and limitations.
© 2026 AI FinTech Index
3801 N Capital of Texas Hwy, Ste E240 · Austin, TX 78746