Skip to Content
Uncategorized

Smart Pages

Xerox technology protects sensitive digital information.
September 1, 2006

Your doctor needs access to all the medical data in your file, but you don’t want the insurance clerks seeing your blood results; besides, that could violate federal privacy laws. Billions of documents–from banking records to personnel files–present similar concerns, which makes for “a pretty gnarly security problem,” says ­Jessica ­Staddon, manager of security research at the Palo Alto Research Center (PARC), the Xerox subsidiary in California.

Illustration by David Plunkert

But scientists at PARC and Xerox’s research laboratory in Webster, NY, are making progress with a technology that automatically protects and selectively reveals information contained in documents, without creating multiple versions of them or hogging as much memory as today’s encryption programs do. In essence, the Xerox software analyzes language to determine whether words and phrases (like “alcohol abuse” or “HIV”), taken in context, are private and should be reserved for doctors, or whether, say, a string of nine digits–potentially a Social Security number–should be seen only by a personnel officer. A single stored form or document reveals its parts according to users’ authorization levels: someone in the hospital scheduling office might see only a patient’s address and phone number.

The researchers are working to make the core technology compatible with existing formats, including PDFs and customized hospital forms. “We’ve scoured the landscape, and there is no technology out there that marries content analysis with encryption so that the whole process becomes automated,” says Shriram Revankar, who heads Xerox’s smart-document lab in Webster.

Such technology is badly needed, says Kenneth H. Buetow, director of the National Cancer Institute’s Center for Bioinformatics in Bethesda, MD. Current privacy laws make it difficult for researchers to share patient data from medical trials. “It represents a potential solution to the sharing of information in compliance with human subjects’ privacy protections,” says Buetow, who is assembling a cancer research database. He cautions that the technology is still unproven; but Xerox hopes it will be ready to commercialize in two to five years.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

It’s time to retire the term “user”

The proliferation of AI means we need a new word.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.