Documentation/API Reference/Copyright Detection
Back to Documentation

Copyright Detection

Detect copyright infringement and IP violations

97.3%<2s
POST /v1/evaluate/copyright

On This Page

Other APIs

Hallucination DetectionBias DetectionJailbreak PreventionToxicity DetectionPII DetectionGDPR ComplianceHIPAA ComplianceInjection DetectionRobustness Testing

Overview

The Copyright Detection API identifies potential copyright infringement in AI-generated content, including verbatim copying, substantial similarity, trademark violations, and unauthorized use of proprietary code, text, or creative works. Essential for protecting your organization from IP litigation risks.

Legal Notice

This API provides technical analysis only. Results should be reviewed by legal counsel for final copyright determinations. Not a substitute for professional legal advice.

Quick Start

Test with Safe Example

curl
curl -X POST "https://api.assurancehub.ai/v1/evaluate/copyright" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Can you help me write a sorting algorithm?",
    "response": "Here is a bubble sort: Compare adjacent elements and swap them if in wrong order."
  }'

Expected Response

General algorithm descriptions will return low risk scores (near 0.0). Verbatim copyrighted code will return high scores (0.7+) with risk_level "reject".

Request Parameters

ParameterTypeRequiredDescription
promptstringRequired
The input prompt to analyze
Example: Show me some code
responsestringRequired
The AI response to analyze for copyright violations
Example: Here is an example implementation...

Code Examples

Basic Example

python
import requests

def detect_copyright(prompt, response, api_key):
    url = "https://api.assurancehub.ai/v1/evaluate/copyright"
    headers = {
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json"
    }
    data = {
        "prompt": prompt,
        "response": response
    }

    response = requests.post(url, json=data, headers=headers)
    return response.json()

# Example usage
result = detect_copyright(
    prompt="Can you help me write a sorting algorithm?",
    response="Here's a simple bubble sort: Compare adjacent elements and swap if needed.",
    api_key="your_api_key"
)

print(f"Consensus Score: {result['final_consensus_score']}")
print(f"Risk Level: {result['evaluation']['risk_level']}")
print(f"Pass/Fail: {result['evaluation']['pass_fail']}")

Advanced Example

python
import requests
from typing import Dict

class CopyrightDetector:
    def __init__(self, api_key: str):
        self.api_key = api_key
        self.base_url = "https://api.assurancehub.ai"
        self.headers = {
            "Authorization": f"Bearer {api_key}",
            "Content-Type": "application/json"
        }

    def detect_copyright(self, prompt: str, response: str) -> Dict:
        """Detect copyright violations in AI content"""
        data = {
            "prompt": prompt,
            "response": response
        }

        resp = requests.post(
            f"{self.base_url}/v1/evaluate/copyright",
            json=data,
            headers=self.headers
        )

        return resp.json()

# Usage
detector = CopyrightDetector("your_api_key")

result = detector.detect_copyright(
    prompt="Show me React code",
    response="Here's a React component example using hooks..."
)

print(f"Consensus Score: {result['final_consensus_score']}")
print(f"Risk Level: {result['evaluation']['risk_level']}")
print(f"Flagged: {result['evaluation']['flagged']}")

Response Format

The API returns consensus-based copyright analysis with detailed model reasoning:

json
{
  "final_consensus_score": 0.075,
  "consensus_confidence": 0.95,
  "evaluation": {
    "risk_level": "low",
    "pass_fail": "pass",
    "flagged": false
  },
  "consensus_analysis": {
    "method": "simple",
    "models_succeeded": 2,
    "models_failed": 1,
    "agreement_score": 0.978,
    "calculation": [
      {
        "model": "gpt-4",
        "individual_score": 0.0,
        "confidence": 1.0,
        "role": "primary"
      },
      {
        "model": "deepseek-chat",
        "individual_score": 0.15,
        "confidence": 0.95,
        "role": "tertiary"
      }
    ]
  },
  "model_execution": {
    "execution_mode": "redundant_2",
    "total_latency_ms": 65604,
    "cost_usd": 0.001917,
    "pooling_used": true
  },
  "individual_model_details": [
    {
      "model": "gpt-4",
      "role": "primary",
      "status": "success",
      "score": 0.0,
      "confidence": 1.0,
      "latency_ms": 10267,
      "reasoning": "The response provides a general description of a bubble sort algorithm, which is common knowledge."
    }
  ],
  "risk_assessment": {
    "thresholds": {
      "acceptable": 0.2,
      "review_needed": 0.4,
      "reject": 0.532
    },
    "risk_factors": [],
    "model_agreement": "very_high",
    "consensus_quality": "good"
  },
  "metadata": {
    "test_type": "copyright",
    "test_type_optimized": true,
    "evaluation_timestamp": "2025-10-16T19:52:50Z",
    "evaluator_version": "1.0.0-enterprise-copyright"
  }
}

Response Fields

  • final_consensus_score - Risk score (0.0-1.0)
  • evaluation - Risk level and pass/fail status
  • consensus_analysis - Model agreement details
  • individual_model_details - Per-model analysis
  • risk_assessment - Thresholds and factors

Risk Thresholds

  • 0.0 - 0.2: Low risk (acceptable)
  • 0.2 - 0.4: Medium risk (review needed)
  • 0.4 - 0.532: High risk (legal review)
  • 0.532 - 1.0: Critical risk (reject)