Image Classification

the below parameters are for various image classification attack types to know more about the different attack input parameters see image classification docid 6deiimjnkl5d0cdwstckb the values presented below are examples taken from the mnist model used in the reference implementation it is important to customize these values to achieve the best performance for your particular model extraction { "attack type" "blackbox", "defense bestonly" "no", "encryption strategy" "0", "input dimensions" "28,28,1", "model api details" "na", "model framework" "tensorflow", "normalize data" "yes", "number of attack queries" "10000", "number of classes" "10", "use model api" "no", "vulnerability threshold" "0 00", "color space" "bgr" } evasion { "defense bestonly" "no", "encryption strategy" "0", "input dimensions" "28,28,1", "model api details" "na", "model framework" "tensorflow", "normalize data" "yes", "number of classes" "10", "use model api" "no", "color space" "bgr" } poisoning { "input dimensions" "28,28,1", "model framework" "tensorflow", "normalize data" "yes", "number of classes" "10", "color space" "bgr" } drift { &#x9;"color space" "bgr", &#x9;"encryption strategy" "0", &#x9;"input dimensions" "128,128,3", &#x9;"model api details" "na", &#x9;"model framework" "tensorflow", &#x9;"use model api" "no", &#x9;"color space" "bgr" } outlier { "input dimensions" "128,128,3" } note in the response, copy job id this value is required to trigger the get apis see \<get> job metadata docid\ s mz7r0hnzicdqy6q 6hq the "job id" is used to retrieve model analysis metadata and check the processing status of the request it is also used for generating reports for the analyzed model copy the dashboard link from the response and open it in a new tab this allows users to monitor the job progress and download reports for using nodejs sample code, install npm package request given ample code for python is tested for python version 3 7 given sample code for nodejs and javascript is tested for node v20lts