> ## Documentation Index
> Fetch the complete documentation index at: https://sc-docs.deepidv.com/llms.txt
> Use this file to discover all available pages before exploring further.

# File Analysis Use Cases

> Banking-specific applications for file deepfake detection

> Protecting document integrity across banking operations — from customer onboarding and credit decisioning to fraud investigation and regulatory compliance.

export const SectionHeader = ({label, title, description, align = "left"}) => <div className="deepidv-section-header" style={{
  textAlign: align,
  alignItems: align === "center" ? "center" : "flex-start"
}}>
    {label && <p className="deepidv-section-label">{label}</p>}
    <h2 className="deepidv-section-title">{title}</h2>
    {description && <p className="deepidv-section-desc">{description}</p>}
  </div>;

export const FeatureGrid = ({cols = 3, children}) => <div className="deepidv-feature-grid" style={{
  "--grid-cols": cols
}}>
    {children}
  </div>;

export const FeatureCard = ({icon, title, description, href}) => {
  const inner = <div className="deepidv-feature-card">
      {icon && <div className="deepidv-feature-card-icon">
          <Icon icon={icon} size={20} />
        </div>}
      <div className="deepidv-feature-card-content">
        <h3 className="deepidv-feature-card-title">{title}</h3>
        {description && <p className="deepidv-feature-card-desc">{description}</p>}
      </div>
      {href && <div className="deepidv-feature-card-arrow">
          <Icon icon="arrow-right" size={14} />
        </div>}
    </div>;
  if (href) {
    return <a href={href} style={{
      textDecoration: "none",
      color: "inherit",
      display: "block",
      border: "none",
      boxShadow: "none"
    }}>
        {inner}
      </a>;
  }
  return inner;
};

<SectionHeader
  label="Document Fraud"
  title={
<>
  Identity Document <span>Verification</span>
</>
}
  description="Detect forged, altered, or AI-generated identity documents submitted during customer onboarding and account opening."
/>

**Scenario:** An applicant submits a passport scan or driver's licence image as part of a remote account opening process. The document appears visually legitimate but has been digitally altered or entirely generated using AI tools.

**What the API detects:**

* AI-generated identity document images created using generative models
* Digitally altered photographs where the applicant's photo has been swapped
* Synthetic document templates that mimic legitimate government-issued formats
* Inconsistent fonts, spacing, or formatting that indicate post-production editing
* Metadata anomalies suggesting the document was produced by image editing software

**Example response:**

```json theme={null}
{
  "analysis_id": "df-id-2025-001",
  "is_ai_generated": true,
  "confidence_score": 87.3,
  "risk_level": "critical",
  "detection_details": [
    {
      "type": "PHOTO_MANIPULATION",
      "description": "Facial photograph shows signs of digital replacement",
      "confidence": 91.2
    },
    {
      "type": "FONT_INCONSISTENCY",
      "description": "Character spacing on line 3 deviates from standard document template",
      "confidence": 78.5
    }
  ]
}
```

***

<SectionHeader
  label="Lending & Credit"
  title={
<>
  Financial Document <span>Integrity</span>
</>
}
  description="Verify the authenticity of bank statements, pay stubs, and tax returns submitted in support of credit and lending applications."
/>

**Scenario:** A loan applicant submits bank statements and pay stubs to demonstrate income and financial stability. The documents have been manipulated to inflate income figures and conceal adverse transaction history.

**What the API detects:**

* Manipulated transaction amounts or balances within bank statement PDFs
* Fabricated financial statements generated using document templates or AI
* Altered dates, account numbers, or institutional branding
* AI-generated financial documents that do not originate from a legitimate financial institution
* Pixel-level editing artifacts in scanned or digital documents

**Example response:**

```json theme={null}
{
  "analysis_id": "df-fin-2025-042",
  "is_ai_generated": false,
  "confidence_score": 72.1,
  "risk_level": "high",
  "detection_details": [
    {
      "type": "CONTENT_MANIPULATION",
      "description": "Transaction amounts on page 2 show evidence of digital alteration",
      "confidence": 82.4
    },
    {
      "type": "METADATA_ANOMALY",
      "description": "PDF creation metadata inconsistent with stated issuing institution",
      "confidence": 65.8
    }
  ]
}
```

***

<SectionHeader
  label="Voice Authentication"
  title={
<>
  Audio & Voice <span>Verification</span>
</>
}
  description="Detect synthetic voice generation and audio manipulation in recorded phone verifications and voice authorization captures."
/>

**Scenario:** A recorded phone verification or voice authorization is submitted as part of a high-value transaction approval process. The voice may have been cloned using publicly available AI voice synthesis tools.

**What the API detects:**

* Synthetic voice generation using text-to-speech or voice cloning models
* Voice cloning artifacts including unnatural prosody and spectral anomalies
* Spliced audio segments where different recordings have been combined
* Background noise inconsistencies suggesting studio or synthetic generation

**Example response:**

```json theme={null}
{
  "analysis_id": "df-audio-2025-018",
  "is_ai_generated": true,
  "confidence_score": 91.6,
  "risk_level": "critical",
  "detection_details": [
    {
      "type": "SYNTHETIC_VOICE",
      "description": "Voice characteristics consistent with AI voice cloning model output",
      "confidence": 93.1
    },
    {
      "type": "SPECTRAL_ANOMALY",
      "description": "Frequency spectrum shows patterns inconsistent with natural human speech",
      "confidence": 88.4
    }
  ]
}
```

***

<SectionHeader
  label="Visual Media"
  title={
<>
  Profile & Media <span>Authentication</span>
</>
}
  description="Verify the authenticity of photographs submitted as proof of identity, business verification, or supporting evidence."
/>

**Scenario:** Profile images or photographs are submitted as part of identity verification, business documentation, or insurance claims. The images may be AI-generated or digitally manipulated to misrepresent the individual or situation.

**What the API detects:**

* AI-generated headshots produced by GAN (Generative Adversarial Network) models
* Manipulated photographs with digitally altered backgrounds, clothing, or context
* GAN-generated faces that exhibit characteristic symmetry and texture patterns
* Image splicing where elements from multiple photographs have been combined

**Example response:**

```json theme={null}
{
  "analysis_id": "df-img-2025-007",
  "is_ai_generated": true,
  "confidence_score": 95.2,
  "risk_level": "critical",
  "detection_details": [
    {
      "type": "GAN_GENERATED_FACE",
      "description": "Facial features exhibit patterns characteristic of GAN-generated imagery",
      "confidence": 96.8
    }
  ]
}
```

***

<Info>
  All file analyses are logged and available in the Admin Console for audit purposes. Navigate to **Settings > Audit Logs** to review analysis history, filter by date range, and export records for regulatory reporting.
</Info>