Question 1

What is a document forgery detection API

Accepted Answer

A document forgery detection API is a programmatic service that accepts document files and returns a structured analysis indicating whether the document shows signs of manipulation, fabrication, or AI generation. It works by combining OCR extraction, metadata analysis, structural template comparison, and machine learning models trained on known forgery patterns, then expressing its findings as a confidence score, risk level, and itemised list of detected signals.

Question 2

How does a document forgery detection API differ from standard OCR

Accepted Answer

Standard OCR extracts text content from a document but makes no judgement about whether that content is genuine. A document forgery detection API goes further by comparing the extracted content and document structure against authoritative templates, checking metadata consistency, analysing font and typographic properties, and examining security features — returning a forensic verdict rather than simply a transcript of the document's text.

Question 3

Is the API compliant with UK GDPR and the EU AI Act

Accepted Answer

CheckFile's API infrastructure is designed to support compliance with both frameworks, including data residency options, encrypted transmission, configurable retention policies, and audit log exports. However, regulatory compliance is a shared responsibility: the controller (your organisation) must establish a lawful basis for processing, maintain appropriate records of processing activities, and configure the integration in accordance with your own data protection policies. The EU AI Act's high-risk classification for document verification systems also places obligations on the deploying organisation, not only the API provider.

Question 4

How long does it take to integrate a document forgery detection API

Accepted Answer

A basic integration using synchronous endpoints — covering authentication, document submission, and response handling — typically takes a backend developer two to four days to implement and test against the sandbox environment. Adding webhook handling for asynchronous workflows, configuring retry logic, and building a manual review queue for flagged documents extends this to approximately one to two weeks. Full production deployment including compliance documentation, staff training, and sign-off from your DPO typically takes four to six weeks depending on your organisation's change management processes.

Question 5

What file formats does a document forgery detection API accept

Accepted Answer

The CheckFile API accepts JPEG, PNG, PDF, TIFF, and HEIC file formats. PDF submissions may contain multiple pages; the API analyses each page individually and returns signals at the page level where relevant. Maximum file size per submission is 20 MB. For mobile capture workflows, HEIC files from iOS devices are accepted without pre-conversion. Where documents are submitted as scanned PDFs, the platform's OCR layer extracts text prior to structural analysis, with support for 24 languages covering the majority of documents encountered in UK and European onboarding contexts.

Question 6

What is anti-fraud technology?

Accepted Answer

Anti-fraud technology refers to software systems and analytical methods designed to detect, prevent, and investigate fraudulent activity. In the context of document verification, it encompasses optical character recognition, digital metadata forensics, machine learning anomaly detection, biometric verification, and behavioural analytics. These technologies work together to identify forged, altered, or fabricated documents without relying on manual visual inspection as the primary control. Anti-fraud technology is distinct from fraud risk management more broadly, which includes transaction monitoring, sanctions screening, and network analytics.

Question 7

How does AI detect forged documents?

Accepted Answer

AI detects forged documents by comparing submitted documents against statistical models trained on large corpora of authentic and fraudulent documents. The process typically operates across several layers simultaneously. Metadata analysis checks whether the hidden file data is consistent with the document's claimed provenance -- for example, whether a tax certificate was created in a word processor rather than by the issuing authority's official system. Font analysis checks whether the typefaces, spacing, and rendering in every zone of the document match the expected signature for that document type. Layout anomaly detection identifies structural deviations -- shifted logos, inconsistent margins, missing elements -- that indicate the document was assembled rather than issued. Cross-reference verification checks whether data points are consistent across multiple documents in the same file. AI-generated fraudulent documents have risen in our platform analysis, making multi-layer detection increasingly important.

Question 8

What are UK legal requirements for document fraud detection?

Accepted Answer

UK organisations subject to the Money Laundering Regulations 2017 must verify customer identity using reliable and independent sources, and maintain adequate and proportionate controls commensurate with the assessed risk of the business relationship. The Economic Crime and Corporate Transparency Act 2023 extended the failure-to-prevent-fraud offence and strengthened Companies House verification requirements. The FCA Financial Crime Guide sets out examples of good practice for regulated firms, explicitly identifying automated document screening as appropriate in high-volume or high-risk settings. There is no prescriptive technical standard mandating a specific technology, but regulators have taken enforcement action against firms whose document controls were demonstrably inadequate -- with fines in the UK financial sector exceeding GBP 100 million between 2022 and 2025 for financial crime control failures. UK firms with EU operations must additionally comply with AMLD6 (Directive 2024/1640), available at EUR-Lex.

Question 9

How much does anti-fraud technology cost?

Accepted Answer

The cost of anti-fraud technology varies significantly by architecture, document volume, and vendor. Individual API-based checks for metadata analysis or OCR typically cost between GBP 0.05 and GBP 0.30 per document at scale. Biometric liveness detection checks typically range from GBP 0.50 to GBP 2.00 per check depending on volume. Full platform solutions that combine multiple detection layers are generally priced on a monthly subscription basis tied to document volume, with per-document effective costs falling as volume increases. The more relevant comparison is total cost of ownership against the cost of manual verification -- typically GBP 8 to GBP 25 per manually reviewed document when analyst time, error rates, and re-work are factored in -- and against the cost of undetected fraud. Our platform data shows an 83% reduction in processing time compared to manual verification workflows. See our pricing page for current CheckFile rates by tier.

Question 10

What is the difference between OCR and AI for fraud detection?

Accepted Answer

OCR (optical character recognition) is the process of extracting text from a document image or PDF and converting it into machine-readable data. It is a prerequisite for most downstream analysis but is not itself a fraud detection technique: OCR tells you what the text says, not whether it has been altered. AI fraud detection uses the extracted text and the document's raw image data as inputs to machine learning models that identify anomalies, inconsistencies, and patterns associated with fraud. A document can pass OCR extraction perfectly -- all text correctly extracted -- while simultaneously triggering AI fraud alerts through font inconsistency, metadata discrepancies, or layout anomalies. In practice, OCR and AI fraud detection are complementary layers in the same pipeline: OCR provides the data, and AI models analyse that data alongside pixel-level and structural features to produce a fraud confidence score.

Automation

Document Forgery Detection API: Integration Guide 2026

Anti-Fraud Technology: Document Detection Tools & Techniques 2026

Liveness Detection: Stop Identity Spoofing (ISO 30107-3)

Compliance Automation: AI for Regulatory Workflows 2026

Manual to AI Verification Migration: Step-by-Step Guide

AI Document Classification: Sorting & Routing

Document Workflow Automation: Automate Document Processing

Compliance Monitoring: Tools & Practices 2026

Legal Document Automation: Contract Automation Guide

Invoice Processing Automation: AP Teams Guide

Supplier Invoice Verification: Detect Fraud and Errors

Document Verification API: Developer Integration Guide

Best Document Verification Software 2026: Comparison

Automated Document Verification: Build vs Buy Guide 2026

Best OCR Software for Document Verification in 2026

DMS Compliance: Regulatory Document Management Guide

How to choose compliance software for your organization

Digital Onboarding KYC: Drop-Offs & Compliance

Document Dematerialization: Go Paperless & Compliant

Electronic Signature and Document Verification

AI Fraud Detection: How Machines Spot Fakes

Deepfakes and Synthetic Documents in 2026

Build vs Buy: Document Validation In-House?

Document Validation: API, Webhooks, and ERP

Cross-Document Validation: Beyond OCR & IDP

Generative AI vs Extraction: Document Validation

Automated Document Verification: Cost & 90% Time Savings