Analyze your models
You can analyze your model for vulnerabilities by using the model analysis API. To test your model, refer to the table below to see the different attack types you can try. Use these attacks to generate vulnerability reports, sample attack vectors, and a threat-informed defense model based on input parameters, data, and model files.
You can use the suggested input parameter configuration or experiment with specific parameters to see how vulnerability reports and threat-informed defense models are generated.
You have to first register your model using <Post> Model Registration API to get started with model analysis. After that there are other APIs which you can use to get <Get> Job Metadata and <Get> Retrieve Artifacts and more.
Supported data input | Task type | Inputs parameters | Model analysis APIs | Usecase | Reference-implementation |
|---|---|---|---|---|---|
Images | Image classification | Inputs | APIs | Recognizing handwritten digits for digit recognition in postal services. | |
| Image segmentation | Inputs | APIs | In medical imaging, segmenting tumor regions from brain MRI scans to assist in diagnosing and treating brain tumors. | |
Tabular | Tabular classification | Inputs | APIs | Predicting customer churn in a telecommunications company based on historical usage data. | |
Time series | Forecasting | Inputs | APIs | Predicting stock prices using time series forecasting | |
Text | Text classification | Inputs | APIs | Categorizing emails as "spam" or "not spam" based on their content. | |
Static Assessment | Supply chain | Inputs | APIs | Scan for serialisation threats, backdoor attacks and any PII, keys leak in Notebook files | |
