tencent cloud

文档反馈

DetectAIFakeFaces

最后更新时间:2024-10-22 17:35:21

1. API Description

Domain name for API request: faceid.tencentcloudapi.com.

Based on the multimodal AI large model algorithm, it provides anti-attack detection capabilities for facial images and videos. It can effectively identify highly simulated AIGC face-changing, high-definition remakes, batch black market attacks, watermarks and other attack traces, and enhance the anti-counterfeiting security capabilities of images and videos.

A maximum of 5 requests can be initiated per second for this API.

We recommend you to use API Explorer
Try it
API Explorer provides a range of capabilities, including online call, signature authentication, SDK code generation, and API quick search. It enables you to view the request, response, and auto-generated examples.

2. Input Parameters

The following request parameter list only provides API request parameters and some common parameters. For the complete common parameter list, see Common Request Parameters.

Parameter Name Required Type Description
Action Yes String Common Params. The value used for this API: DetectAIFakeFaces.
Version Yes String Common Params. The value used for this API: 2018-03-01.
Region No String Common Params. This parameter is not required.
FaceInput No String Enter the image or video with a face to be detected, in base64 encoding. Base64 value of the image: The overall image resolution is recommended to be 480x640, and the face size is 100X100 or larger; The image data size after Base64 encoding does not exceed 3M, and only supports jpg and png formats. Please use standard Base64 encoding (use = for padding). Refer to RFC4648 for encoding specifications. Base64 value of the video: The size after Base64 encoding does not exceed 8M, and supports mp4, avi, and flv formats. Please use standard Base64 encoding (use = for padding). Refer to RFC4648 for encoding specifications. The maximum supported video length is 20s, and the recommended length is 2 to 5s. The recommended video resolution is 480x640, and the frame rate is between 25fps and 30fps.
FaceInputType No Integer The type of input is 1- The input type is a picture 2- The input type is a video Others - Return error code InvalidParameter
Encryption No Encryption Whether the request information needs to be fully encrypted; Supported encryption algorithms: AES-256-CBC, SM4-GCM; Users with encryption requirements can use this parameter, for details, please click the link on the left.
EncryptedBody No String Encrypted ciphertext; The data format before encryption is as follows:{"FaceInput":"AAAAA","FaceInputType":1}

3. Output Parameters

Parameter Name Type Description
AttackRiskLevel String Whether the detected image is an attack: Low: No attack risk Mid: Moderately suspected attack High: Highly suspected attack
AttackRiskDetailList Array of AttackRiskDetail A list of suspected attack traces detected. Note: When no attack traces are detected, an empty array is returned. This parameter is only used as a reference for result judgment. In actual applications, it is still recommended to use the result of AttackRiskLevel.
ExtraInfo ExtraInfo Additional Information
RequestId String The unique request ID, generated by the server, will be returned for every request (if the request fails to reach the server for other reasons, the request will not obtain a RequestId). RequestId is required for locating a problem.

4. Example

Example1 Unencrypted request example

Suspected high-risk attack

Input Example

POST / HTTP/1.1
Host: faceid.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: DetectAIFakeFaces
< Common request parameters >

{
    "FaceInputType": 1,
    "FaceInput": "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"
}

Output Example

{
    "Response": {
        "AttackRiskDetailList": [
            {
                "Type": "SuspectedWatermark"
            }
        ],
        "AttackRiskLevel": "High",
        "RequestId": "2dd93e6f-5121-4bac-8c64-d6ad646663d2"
    }
}

Example2 Exception Example

Image decoding failed

Input Example

POST / HTTP/1.1
Host: faceid.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: DetectAIFakeFaces
< Common request parameters >

{
    "FaceInputType": 2,
    "FaceInput": "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"
}

Output Example

{
    "Response": {
        "Error": {
            "Code": "FailedOperation.ImageDecodeFailed",
            "Message": " Image decoding failed."
        },
        "RequestId": "0e77ad29-ad65-4901-9efc-b49a6e0a357b"
    }
}

Example3 Example of a full-body encrypted request

Example of a full-body encrypted request

Input Example

POST / HTTP/1.1
Host: faceid.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: DetectAIGCContent
< Common request parameters >

{
    "Encryption": {
        "Algorithm": "AES-256-CBC",
        "EncryptList": [
            "EncryptionBody"
        ],
        "CiphertextBlob": "qwRTgn+52FAvnfrGL1oPBsXG4FLBd42YRw",
        "Iv": "vqfsaEOpGJESA=="
    },
    "EncryptedBody": "v32onREKL6bk6WHOGFEjE2M6kvqybGCVTjlm"
}

Output Example

{
    "Response": {
        "AttackRiskDetailList": [
            {
                "Type": "SuspectedWatermark"
            }
        ],
        "AttackRiskLevel": "High",
        "RequestId": "2dd93e6f-5121-4bac-8c64-d6ad646663d2"
    }
}

5. Developer Resources

SDK

TencentCloud API 3.0 integrates SDKs that support various programming languages to make it easier for you to call APIs.

Command Line Interface

6. Error Code

The following only lists the error codes related to the API business logic. For other error codes, see Common Error Codes.

Error Code Description
FailedOperation.CoveredFace The face in the picture is blocked, please upload a picture without any blockage
FailedOperation.DetectEngineSystemError The service engine call failed, please try again
FailedOperation.ImageDecodeFailed Image decoding failed.
FailedOperation.IncompleteFace No complete face was detected. Please enter a complete face image.
FailedOperation.PoorImageQuality The image quality is too poor, please check the image quality
FailedOperation.UnKnown Unknown internal error.
FailedOperation.VideoDecodeFailed Video decoding abnormality
InvalidParameter Invalid parameter.
InvalidParameterValue Incorrect parameter value.
UnauthorizedOperation.Arrears The account is in arrears.
UnauthorizedOperation.ChargeStatusException The billing status is abnormal.
UnauthorizedOperation.Nonactivated The service has not been activated.
联系我们

联系我们,为您的业务提供专属服务。

技术支持

如果你想寻求进一步的帮助,通过工单与我们进行联络。我们提供7x24的工单服务。

7x24 电话支持