Don’t Compromise Data Access or Data Sensitivity
Stained Glass Transform™ is a new category of AI and privacy-enhancing technology that enables you to extract ML insights from from you data while protecting against the leakage of sensitive information. Get the best of data access and protection.
How it works
Stained Glass takes data from your root of trust and generates a Randomized Re-Representation of the data, specifically tailored for the designated ML task, ensuring data security. If data is compromised, a malicious actor encounters its Randomized Re-Representations, which hold no value.
Increase Real data in ML for Better Outcomes.
Worry less about data exposure.
Preempt Data Leakage at Every Stage of your Machine Learning
Protect your Data during Both ML Training and ML Deployment
STG for Training Unblock Data Sensitivity Frictions to Train Models that Perform
Use more real data, make the case for what you only need vs. what is confidential. Fulfill protocols and train models with more real-world data for better predictions.
STG for ML Inferencing Solve for Data Privacy in the ML deployment stage for any data type
The biggest AI vulnerability is during ML deployment. Enterprises lack consistent protection for the ML deployment phase. Stained Glass bridges the gap with transformations on any data-type
Choose your data type
Protopia AI in Action with Face Recognition
Most face recognition models would see a data record in its fully exposed form as it appears to the left. This exposes all the information in plain/raw form to the prediction task. With Protopia AI’s Stained Glass Transform™ in place, the model sees a completely transformed data record as shown on the right, and can still do accurate inferencing with minimal information.
Watch Protopia help an ML task make a prediction on a loan application with the example below.
Traditionally, a model would look at every piece of data in the data record and a combination of all those pieces of information in raw form. This approach enables the leaking of sensitive information about the application such as PII. With Protopia in place, the model will read a completely transformed and randomized piece of data but still be able to predict the outcome with the same level of accuracy.
Notice how the personally sensitive attributes on the left are obfuscated on the right with the stochastic embedded representation. In addition, the reconstructed information of text and numbers does not match the actual data depicted on the left. That’s a transformation that automatically occurs in this process.
Watch Protopia in action with an NLP task performing phishing email detection.
However, current NLP tasks have the opportunity to consume data that contains too much sensitive information such as email content. The left side below shows what the tokenized version of emails look like today when using NLP services. On the right, using Protopia’s stochastic transformations, you’ll see how we help protect sensitive information while still enabling an NLP task to identify spam and work accurately.
- Visual Data
-
Protopia AI in Action with Face Recognition
Most face recognition models would see a data record in its fully exposed form as it appears to the left. This exposes all the information in plain/raw form to the prediction task. With Protopia AI’s Stained Glass Transform™ in place, the model sees a completely transformed data record as shown on the right, and can still do accurate inferencing with minimal information.
- Structured/Tabular Data
-
Watch Protopia help an ML task make a prediction on a loan application with the example below.
Traditionally, a model would look at every piece of data in the data record and a combination of all those pieces of information in raw form. This approach enables the leaking of sensitive information about the application such as PII. With Protopia in place, the model will read a completely transformed and randomized piece of data but still be able to predict the outcome with the same level of accuracy.
Notice how the personally sensitive attributes on the left are obfuscated on the right with the stochastic embedded representation. In addition, the reconstructed information of text and numbers does not match the actual data depicted on the left. That’s a transformation that automatically occurs in this process.
- Natural Language Processing
-
Watch Protopia in action with an NLP task performing phishing email detection.
However, current NLP tasks have the opportunity to consume data that contains too much sensitive information such as email content. The left side below shows what the tokenized version of emails look like today when using NLP services. On the right, using Protopia’s stochastic transformations, you’ll see how we help protect sensitive information while still enabling an NLP task to identify spam and work accurately.
Access and Share Data with Previously Inaccessible SaaS solutions
Overcome sensitive data restrictions and take advantage of cost-effective cloud, AI and SaaS solutions
