Image Classification

8min

The below input parameters are for different attack types. To start working with the APIs view the Image Classification﻿. 
File upload format
Data: The processed data, ready to be passed to the model for prediction, should be saved in a folder.
﻿Download sample data﻿
Label: A CSV file should be created with two columns: "image" and "label." The first column should contain the image name, and the second column should contain the label. The label should be in integer format. Check sample label file attached.
﻿Download sample label﻿
Model: The model should be saved in either .h5 or TensorFlow format with full architecture. Full architecture is needed when loading the model to the platofrm for assessment either in encrypted or unencrypted. This can be ignored when model is hosted as an API.
﻿Download sample model﻿
Note:
 All files uploaded should be in zipped format. The above files are sample data for the MNIST use case.
 Prerequisite: Only 2-5 % of data is needed. The data should be representative and balanced  across all classes.
For poisoning, check poisoning section to get sample data, label and models. 
Common parameters
The below table parameters are common for all attact types such as Extraction, Evasion, and Poisoning. 
To see the additional parameter specific for each attact type, such as Extraction and Evasion, refer to the below sections. 
Parameter
Data type
Description
Remark
model_Id
String
Model_id received during model registration. 
We need to provide this model ID in query parameter in URL.
You have to do model registration only once for a model to perform model analysis. This will help you track the no of api call made, and it's success metric.
Request Body (Json format)
﻿
﻿
﻿
normalize_data 
String
Model trained on Normalized data.
if model is trained on normalized data, then set this parameter as "yes" else "no".
input_dimensions  
String
Provide input dimension of the image 
the parameter should be string in the format "(height, weight, channel)" For example 28*28*1 for MNIST
number_of_classes 
String
Number of prediction classes.  
the parameter should be string. Example MNIST : 10 (Range >0 & <=200)
model_framework 
String
Original model is built with tensorflow framework. 
curretly supported framework are: tensorflow, scikit-learn, keras. (Option:[tensorflow])
﻿
Parameter
Data type
Description
Remark
Request Body (Json format)
﻿
﻿
﻿
attack_type 
String
You can select the attack type either Blackbox or Greybox. 
Blackbox: for performing model analysis, no information about model or data will be used.                                              Greybox: information about data will be leverage for creation of attack data              Note: only 2-5 % of data is needed
number_of_attack_queries 
String
Number of attack queries that model will be 
subjected to.
generally Heigher the number of attack queries, better would be the analysis. And it would take more time to process. (Range:  >0 & <=400000)
vulnerability_threshold 
String
Threshold percent of stolen model accuracy 
at which defense model should be generated.
Threshold percent of stolen model accuracy 
at which defense model should be generated 
(Range :  0.0 - 1)
model_api_details
String
If use_model_api is Yes, then provide API 
details of hosted model as encrypted JSON 
string is mandatory
provide this only if use_model_api is "yes". 
use_model_api 
String
Use model API to train your model instead of uploading the model as a zip file.
when this parameter is yes, you don't have to upload model as zip. You can pass api url along with other verification credential in json file. 
defense_bestonly 
﻿
String
Choose to train your model until it achieves the best results or above 95% accuracy.
when selected "yes", it will train N number of model and select best model. Ofcourse this will take longer time. If "no", then once defense model accuracy reached above 95% It will stop 
encryption_strategy
Int
Choose a encryption strategy for you model. if model is uploaded directly as a 
zip pick 0, 1 if model is encryted as .pyc and 
uploaded as a zip. Ignore if use_model_api is 
Yes
select 0: pass tensorflow model as it is, select 1: pass encrypted model. It could be .pyc file 
Parameter
Data type
Description
Remark
Request Body (Json format)
﻿
﻿
﻿
model_api_details 
String
If use_model_api is Yes, then provide API details of hosted model as encrypted JSON string is mandatory
provide this only if use_model_api is "yes". 
use_model_api
String
Use model API to train your model instead of uploading the model as a zip.
when this parameter is yes, you don't have to upload model as zip. You can pass api url along with other verification credential in json file. 
defense_bestonly
String
Choose to train your model until it achieves the best results or above 95% accuracy.
when selected "yes", it will train N number of model and select best model. Ofcourse this will take longer time. If "no", then once defense model accuracy reached above 95% It will stop 
encryption_strategy
Int
Choose a encryption strategy for you model. if model is uploaded directly as a zip pick 0, 1 if model is encryted as .pyc and uploaded as a zip. Ignore if use_model_api is Yes
select 0: pass tensorflow model as it is, select 1: pass encrypted model. It could be .pyc file 
 Reference data : The reference images or the clean images should be saved in a folder.
﻿Download sample reference data﻿
Reference label : A CSV file should be created with two columns: "image" and "label." The first column should contain the image name, and the second column should contain the label. The label should be in integer format. Check sample label file attached.
﻿Download sample reference label﻿
Test data :  Dataset under test that might contain drifted images.
﻿Download sample test data﻿
Test label : A csv file containing corresponding labels to the universal data, two 
columns: ‘image’ and ‘label’. The ‘image’ column contains the image name including the extension, and the second column should contain the label. The label should be in integer format.
﻿Download sample test label﻿
Date :  Data in a ZIP format needs to be checked for the presence of outliers.
﻿Download sample data﻿
Data Poisoning
Universal Dataset : Data containing potential poisoning data that needs to
be tested.
﻿Download sample universal dataset  
Universal Label : A csv file containing corresponding labels to the
universal data, two columns: ‘image’ and ‘label’. The ‘image’ column contains the imagename including the extension, and the second column should contain the label. The label should be in integer format.
﻿Download sample universal label﻿
Data : The processed data, ready to be passed to the model for prediction, should be saved in a folder.
﻿Download sample data﻿
Label : A CSV file should be created with two columns: "image" and "label." The first column should contain the image name, and the second column should contain the label. The label should be in integer format. Check sample label file attached.
﻿Download sample label ﻿
Model : The model should be saved in either .h5 or TensorFlow format with full architecture. Full architecture is needed when loading the model to the platform for assessment.
﻿Download sample model

To improve the accuracy, you can experiment with the following values for your attack input parameters. In our example we have used an MNIST dataset in our model and the below table reflects the parameters suitable for it. For more information, please refer to the reference implementation.
Task Pair/Analysis Type
Type of Attack Strategy 
No of queries 
Outcome
Extraction
Blackbox
60000 
Stolen model accuracy between 85%-90%
Extraction
Greybox
20000
Stolen model accuracy above 90%
Evasion
N/A
N/A
Evasion report
Poisoning
N/A
N/A
Model is poisoned or not.
To access all sample artifacts, please visit Artifacts﻿. 
For specific artifact details,  refer 
Vulnerability Report : Vulnerability Report﻿     
Sample Attacks : Sample Attacks﻿﻿
Defense Report: Defense Report﻿                    
Defense Model: Defense Model﻿﻿
Note: For Image classification, supported attack types are - Extraction, Evasion and Poisoning, Drift and Outlier.
﻿

Parameter	Data type	Description	Remark
model_Id	String	Model_id received during model registration. We need to provide this model ID in query parameter in URL.	You have to do model registration only once for a model to perform model analysis. This will help you track the no of api call made, and it's success metric.
Request Body (Json format)
normalize_data	String	Model trained on Normalized data.	if model is trained on normalized data, then set this parameter as "yes" else "no".
input_dimensions	String	Provide input dimension of the image	the parameter should be string in the format "(height, weight, channel)" For example 28281 for MNIST
number_of_classes	String	Number of prediction classes.	the parameter should be string. Example MNIST : 10 (Range >0 & <=200)
model_framework	String	Original model is built with tensorflow framework.	curretly supported framework are: tensorflow, scikit-learn, keras. (Option:[tensorflow])

Parameter	Data type	Description	Remark
Request Body (Json format)
attack_type	String	You can select the attack type either Blackbox or Greybox.	Blackbox: for performing model analysis, no information about model or data will be used. Greybox: information about data will be leverage for creation of attack data Note: only 2-5 % of data is needed
number_of_attack_queries	String	Number of attack queries that model will be subjected to.	generally Heigher the number of attack queries, better would be the analysis. And it would take more time to process. (Range: >0 & <=400000)
vulnerability_threshold	String	Threshold percent of stolen model accuracy at which defense model should be generated.	Threshold percent of stolen model accuracy at which defense model should be generated (Range : 0.0 - 1)
model_api_details	String	If use_model_api is Yes, then provide API details of hosted model as encrypted JSON string is mandatory	provide this only if use_model_api is "yes".
use_model_api	String	Use model API to train your model instead of uploading the model as a zip file.	when this parameter is yes, you don't have to upload model as zip. You can pass api url along with other verification credential in json file.
defense_bestonly	String	Choose to train your model until it achieves the best results or above 95% accuracy.	when selected "yes", it will train N number of model and select best model. Ofcourse this will take longer time. If "no", then once defense model accuracy reached above 95% It will stop
encryption_strategy	Int	Choose a encryption strategy for you model. if model is uploaded directly as a zip pick 0, 1 if model is encryted as .pyc and uploaded as a zip. Ignore if use_model_api is Yes	select 0: pass tensorflow model as it is, select 1: pass encrypted model. It could be .pyc file

Parameter	Data type	Description	Remark
Request Body (Json format)
model_api_details	String	If use_model_api is Yes, then provide API details of hosted model as encrypted JSON string is mandatory	provide this only if use_model_api is "yes".
use_model_api	String	Use model API to train your model instead of uploading the model as a zip.	when this parameter is yes, you don't have to upload model as zip. You can pass api url along with other verification credential in json file.
defense_bestonly	String	Choose to train your model until it achieves the best results or above 95% accuracy.	when selected "yes", it will train N number of model and select best model. Ofcourse this will take longer time. If "no", then once defense model accuracy reached above 95% It will stop
encryption_strategy	Int	Choose a encryption strategy for you model. if model is uploaded directly as a zip pick 0, 1 if model is encryted as .pyc and uploaded as a zip. Ignore if use_model_api is Yes	select 0: pass tensorflow model as it is, select 1: pass encrypted model. It could be .pyc file

Task Pair/Analysis Type	Type of Attack Strategy	No of queries	Outcome
Extraction	Blackbox	60000	Stolen model accuracy between 85%-90%
Extraction	Greybox	20000	Stolen model accuracy above 90%
Evasion	N/A	N/A	Evasion report
Poisoning	N/A	N/A	Model is poisoned or not.

Updated 26 Dec 2024

Did this page help you?

Image

Object Detection

Image Classification

File upload format

Common parameters

Extraction parameters

Evasion Parameters

Drift

Outlier

Poisoning

Experimentation with values