Text Classification
The below input parameters are for different attack types. To start working with the APIs, see Text Classification.
Text classification is an early access with limited functionality. It is not available in AIShield pypi package. For early access, kindly contact [email protected]
- Data: The processed data, ready to be passed to the model for prediction, should be saved in a folder.
- Model: The model should be saved in either .h5 or TensorFlow format with full architecture along with token in .pkl format. Also there need to be a base_model.py file which should load model and token and confire it to give prediction. All Three file base_model.py, .h5 saved model and .pkl saved token should be zipped in a folder and uploaded.
The below table parameters are common for Extraction Attack type.
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) | | | |
model_api_details | String | Use model API to train your model instead of uploading the model as a zip file. Yes | provide this only if use_model_api is "yes". |
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 |
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 text (100) | the parameter should be string in the format. For example 100. |
number_of_attack_queries | String | Number of attack queries that model will be subjected to. e.g. 20000 | generally Heigher the number of attack queries, better would be the analysis. And it would take more time to process. (Range: >0 & <=400000) |
model_framework | String | Original model is built with tensorflow framework. | curretly supported framework are: tensorflow, scikit-learn, keras. (Option:[tensorflow]) |
vulnerability_threshold | String | Number of attack queries that model will be subjected to. e.g, 0.0 - 1 | Threshold percent of stolen model accuracy at which defense model should be generated (Range : 0.0 - 1) |
defense_best_only | 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 |
To access all sample artifacts, please visit Artifacts.
- For specific artifact details, refer
Note: For Text classification, supported attack types are - Extraction
