Detect tampering in a document image

Analyze one document-page image for tampering and AI editing, and get back a verdict plus any localized tampered regions (bounding boxes in original-image pixels). Synchronous but slow — about 5 to 90 seconds per image (more on a cold start) — so call it from a background job with a long timeout, not in a user-facing request. Send a single image; to analyze a PDF, rasterize each page to an image and call once per page. Requires an API key with the document-image scope.

Authorization

BearerAuth

AuthorizationBearer <token>

Send your secret API token as a bearer token in the Authorization header: Authorization: Bearer <token>. Keep it server-side and never expose it in client code.

In: header

Request Body

multipart/form-data

TypeScript Definitions

Use the request body type in TypeScript.

file*file

One document-page image — png, jpg, jpeg, webp, or tiff (not a PDF). Up to 25 MB by default.

Response Body

`application/json`

cURL

curl -X POST "https://example.com/api/app/document-deepfake/detect" \  -F file="string"

import requestsurl = "https://example.com/api/app/document-deepfake/detect"body = {  "file": "string"}response = requests.request("POST", url, data = body, headers = {  "Content-Type": "multipart/form-data"})print(response.text)

package mainimport (  "fmt"  "net/http"  "io/ioutil"  "mime/multipart"  "bytes")func main() {  url := "https://example.com/api/app/document-deepfake/detect"  body := new(bytes.Buffer)  mp := multipart.NewWriter(payload)  mp.WriteField("file", `string`)  req, _ := http.NewRequest("POST", url, body)  req.Header.Add("Content-Type", "multipart/form-data")  res, _ := http.DefaultClient.Do(req)  defer res.Body.Close()  body, _ := ioutil.ReadAll(res.Body)  fmt.Println(res)  fmt.Println(string(body))}

import java.net.URI;import java.net.http.HttpClient;import java.net.http.HttpRequest;import java.net.http.HttpResponse;import java.net.http.HttpResponse.BodyHandlers;import java.time.Duration;import java.net.http.HttpRequest.BodyPublishers;var body = BodyPublishers.ofByteArray(new byte[] { ... });HttpClient client = HttpClient.newBuilder()  .connectTimeout(Duration.ofSeconds(10))  .build();HttpRequest.Builder requestBuilder = HttpRequest.newBuilder()  .uri(URI.create("https://example.com/api/app/document-deepfake/detect"))  .header("Content-Type", "multipart/form-data")  .POST(body)  .build();try {  HttpResponse<String> response = client.send(requestBuilder.build(), BodyHandlers.ofString());  System.out.println("Status code: " + response.statusCode());  System.out.println("Response body: " + response.body());} catch (Exception e) {  e.printStackTrace();}

{
  "edited": true,
  "score": 0.82,
  "threshold": 0.5,
  "imageWidth": 1654,
  "imageHeight": 2339,
  "meanConfidence": 0.78,
  "fileName": "passport-page-1.png",
  "processingTimeMs": 82140,
  "errorMessage": null,
  "regions": [
    {
      "x": 512,
      "y": 880.5,
      "width": 240,
      "height": 52,
      "score": 0.91,
      "meanScore": 0.63,
      "areaFraction": 0.0032
    }
  ]
}

File too large

{
  "error": {
    "code": "IMAGE_FORENSICS:FILE_TOO_LARGE",
    "message": "File photo.jpg exceeds the maximum size of 50 MB."
  }
}

Unsupported format

{
  "error": {
    "code": "IMAGE_FORENSICS:UNSUPPORTED_FORMAT",
    "message": "Unsupported file format. Allowed — jpg, jpeg, png, webp, heic, heif, tiff."
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "Invalid or missing API token."
  }
}

{
  "error": {
    "code": "api_key.scope_missing",
    "message": "This API key is not authorized for the document-image scope."
  }
}

Detect tampering in a document image

Authorization

Request Body

Response Body

200application/json

400application/json

401application/json

403application/json

`application/json`

`application/json`

`application/json`

`application/json`