Object Detection

3 min

The below parameters are for various Object Detection attacks. To know more about the different attack input parameters see Object Detection

The values presented below are examples taken from the YOLO model used in the reference implementation. It is important to customize these values to achieve the best performance for your particular model.

Json Payload

{
"normalize_data": "yes",
"model_framework": "onnx",
"defense_bestonly": "no",
"model_api_details": "na",
"use_model_api": "no",
            
}

Model anaylsis

POST

https://api.aws.boschaishield.com/prod/api/ais/v1.5/model_analyse

import requests

modelID="<< Enter Model ID >>"
url = "https://api.aws.boschaishield.com/prod/api/ais/v1.5/model_analyse/"+modelID+""

# please select proper payload for your usecase for extraction, evasion or poisoning.
payload={
    # <<Enter Payload Data>>
}
headers = {
   'Accept': 'application/json',
   'x-api-key': '########################################',
   'Org-Id': '####################################################################################################'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

Note: In the response, job_id and dashboard link will be available. Save these which would be used to track progress and download artifacts.

For using Nodejs sample code, install npm package request
Given sample code for python is tested for Python version 3.7
Given Sample code for nodejs and javascript is tested for Node V20LTS