Skip to content
Sign in
Artwork for Machine Learning Tech Brief By HackerNoon
Machine Learning Tech Brief By HackerNoon · October 6 · 11 min

Why I Don't Use AI to Remove PII Before Sending Data to AI

This story was originally published on HackerNoon at: https://hackernoon.com/why-i-dont-use-ai-to-remove-pii-before-sending-data-to-ai. If an AI model sees your raw PII before redacting it, the privacy boundary has already moved.The reason I chose deterministic redaction instead. Check more stories related to machine-learning at: https://hackernoon.com/c/machine-learning. You can also check exclusive content about #ai, #pii-detection, #data, #ai-agents, #generative-ai, #how-to-redact-data, #api, #ai-based-redaction, and more. This story was written by: @raviteja-nekkalapu. Learn more about this writer by checking @raviteja-nekkalapu's about page, and for more stories, please visit hackernoon.com. The author of the article is uncomfortable with AI-based redaction because the redaction model still needs to see the original data, which can compromise privacy. They propose a deterministic approach to PII detection and redaction, using validation and checksums to identify and remove sensitive information.

0:00-11:04
Play in

transcript

No transcript — this publisher did not publish one.

show notes

This story was originally published on HackerNoon at: https://hackernoon.com/why-i-dont-use-ai-to-remove-pii-before-sending-data-to-ai.
If an AI model sees your raw PII before redacting it, the privacy boundary has already moved.The reason I chose deterministic redaction instead.
Check more stories related to machine-learning at: https://hackernoon.com/c/machine-learning. You can also check exclusive content about #ai, #pii-detection, #data, #ai-agents, #generative-ai, #how-to-redact-data, #api, #ai-based-redaction, and more.

This story was written by: @raviteja-nekkalapu. Learn more about this writer by checking @raviteja-nekkalapu's about page, and for more stories, please visit hackernoon.com.

The author of the article is uncomfortable with AI-based redaction because the redaction model still needs to see the original data, which can compromise privacy. They propose a deterministic approach to PII detection and redaction, using validation and checksums to identify and remove sensitive information.

links13

more episodes

All episodes