Thanks Martin for bringing this out. I will give this a try. Is it possible to deidentify before sending to the model and add the personal data back once it is retrieved from the model? Use case would be a school document service where the student information in a document would need to be stripped before sending to the model and added back to the response to the user. ?
Good question! Yes, it's called "re-identifying" data in the docs for the Data Loss Prevention API. If you do a web search for "google dlp reidentify quickstart" you'll see a tutorial that walks you through the process step-by-step.
День тому+1
There are techniques proposed by the DLP library to do it. For example: Reversible transformations When you de-identify data using the CryptoReplaceFfxFpeConfig or CryptoDeterministicConfig infoType transformations, you can re-identify that data, as long as you have the CryptoKey used to originally de-identify the data. For more information, see Crypto-based tokenization transformations.
Good point! The Dataloss Prevention API is focused on preventing loss of sensitive text. For facial detection, you can use Google's Vision API. It can pinpoint faces, tell you if the person is wearing headwear, and if they are smiling, frowning, etc.
When I used this API, latency varied a lot with the type and amount of data I sent to it. You can try it out with your data at no cost, as the first 1 GB of data per month is free.
Check out more episodes of Serverless Expeditions with Martin Omander. → goo.gle/ServerlessExpeditions
Thanks Martin for bringing this out. I will give this a try. Is it possible to deidentify before sending to the model and add the personal data back once it is retrieved from the model?
Use case would be a school document service where the student information in a document would need to be stripped before sending to the model and added back to the response to the user. ?
Good question! Yes, it's called "re-identifying" data in the docs for the Data Loss Prevention API. If you do a web search for "google dlp reidentify quickstart" you'll see a tutorial that walks you through the process step-by-step.
There are techniques proposed by the DLP library to do it. For example:
Reversible transformations
When you de-identify data using the CryptoReplaceFfxFpeConfig or CryptoDeterministicConfig infoType transformations, you can re-identify that data, as long as you have the CryptoKey used to originally de-identify the data. For more information, see Crypto-based tokenization transformations.
How to secure data in public cloud using AI .pls give demo video
I know. Only an example. But shouldn’t the image of the person + signature also be redacted in 4:12 ?
Good point! The Dataloss Prevention API is focused on preventing loss of sensitive text. For facial detection, you can use Google's Vision API. It can pinpoint faces, tell you if the person is wearing headwear, and if they are smiling, frowning, etc.
How much latency does this call add ?
When I used this API, latency varied a lot with the type and amount of data I sent to it. You can try it out with your data at no cost, as the first 1 GB of data per month is free.
🌺❤️🌺👍
See your flowery comments every week cheers me up 🙂