Slashdot Mirror
Xerox's 'Intelligent Redaction' Scanners
coondoggie writes "Xerox today touted software it says can scan documents, understand their meaning and block access to those sensitive or secure areas so that prying eyes cannot read, copy or forward the information. Xerox and researchers from its Palo Alto Research Center debuted "Intelligent Redaction," new software that automates the process of removing confidential information from any document. The software includes a detection tool that uses content analysis and an intelligent user interface to protect sensitive information. It can encrypt only the sensitive sections or paragraphs of a document, a capability previously not available, Xerox said."
Don't you mean censorship ?
Putting aside the fact that OCR and related AI is still just this side of "not very good," for an AI to sucessfully and exclusively redact certain material, someone still has to at some point define the dataset of what is redactable, and feed that data into the machine. Unless, of course, this AI is simply allowed to crawl the networks and glean for itself what's good and bad for us...
Slashdot Burying Stories About Slashdot Media Owned
After actually going to the Xerox website and reading about this new technology, I see that it is built around document routing (for review, for example) and has nothing whatsoever to do with their copier and MFD products. This makes sense, considering that they purchased A***** (can't remember the name), which handles legal discovery production and organization services for several corporations (SCO included). Xerox ("The Document Company") is more than just copiers these days.
--Insert catchy
the description given as "computer understands what you write" is an AI-complete issue.
So unless you've seen little robots lying around pondering about life and how superficial data was, I don't see that happening any time soon.
I've done some research on exactly the same issue, and let me tell you, the scientific community is light years away from "text understanding".
What we do in such cases is quite simple. I believe this is a classic search scenario. Given documents/lines/terms/ontology-members that are defined as "sensitive" and then apply X algorithm to detect them in all documents coming in for search.
Every algorithm has it's own pro's and con's mainly measured by their false positives and false negatives, each one suiting their ones own need. Algo's with very few missed positives end up having a LOT of false positives and vice versa.
So you either accept quite a few secrets not getting detected by the system or you accept very few secrets leaking out and a lot of normal text also blacked out.
I'm all for just printing black pages "just to be safe"
So, I either see the poster spewing crap to dramatize the slashdot post (what a surprise!) or the classic marketing people going mental and talk about things they have no idea about.
Hell, I won't even bother to check the xerox announcement.
Stay away from this tech.