Xerox Unveils Technology That Blocks Access to Sensitive Data in Documents to Prevent Security Leaks
15 October 2007
- The News: Xerox and PARC have developed technologies that control access to sensitive information and make it possible to remove data for readers who don't have a "need to know."
- The Context: Organizations such as financial services and mortgage businesses depend on easy access to digital documents. Digitized content can be printed, copied, forwarded and reused, making it hard to control information and comply with privacy restrictions.
- The Innovation: The technology includes a detection software tool that uses content analysis and an intelligent user interface to easily protect sensitive information. It can encrypt only the sensitive sections or paragraphs of a document, a capability previously not available.
PALO ALTO, Calif., Oct. 15, 2007 -- Xerox Corporation (NYSE: XRX) researchers from Palo Alto Research Center, Inc. (PARC) today demonstrated for the first time a new software technology that will greatly increase accuracy while reducing the time needed to remove sensitive or confidential material from documents.
Dubbed "Intelligent Redaction," the new software automates the process of removing confidential information from any document. Once users have identified the information they want to protect, the software automatically redacts all references to this information throughout the document. After information has been classified, that same information will be automatically redacted if it appears in other documents. This "intelligence" ensures a consistent level of security, saves time and increases redaction accuracy.
The research aligns with Xerox's goal of developing smarter documents to make information-based work easier, more efficient and more effective.
Still in development, the innovative technology combines PARC's security and privacy, natural language, and user interface design expertise to develop semi-automated ways to identify and protect sensitive content. The intelligent redaction technology also creates a behind-the-scenes audit trail should the document or information be compromised.
In today's world virtually all data including personalized financial, customer, employee and confidential corporate data is stored digitally. The new technology responds to a growing problem -- protecting sensitive data.
"The tools available today can't provide sufficient content analysis and security because it's difficult to determine what is sensitive," according to Jessica Staddon, manager of the security research area at PARC. "In a large organization the level of sensitivity changes depending on the person accessing the document. The sheer numbers of documents to be tracked and sorted further complicates the problem."
Now you see it. Now you don't.
Redaction is the ability to control what someone sees. For example, redaction traditionally has been used in legal documents to limit access to information protected by client-attorney privilege. The result is a document that has been censored; certain information within the document is blocked out.
Traditional redaction has two big drawbacks. It requires a labor-intensive manual process to identify sections to censor, and management of different versions of the same document is cumbersome and difficult. PARC's intelligent redaction removes these obstacles. The user interface makes it easy for the document owner or author to identify the sensitive data. Then the security tools protect the sensitive information by allowing the document itself to hide or expose information or data within it, based on who has been granted access.
How it works
Current software encrypts whole documents. Intelligent redaction understands document context so it can perform partial encryption. Only sensitive sections or paragraphs are encrypted, while the rest of the document is not. The intelligent redaction software also displays or hides restricted portions of the document. Now the document appears different to different people.
The new software automates the process of removing confidential information in three steps. The software first analyzes the content of the document automatically and identifies entities of interest such as the names of persons or companies, topics, addresses, and identification numbers and the relationships between them such as two people living at the same address.
The next step is for the author to review the document, highlight entities of interest, and trace the relationship between entities. This simplifies the task of finding all sensitive information in a document and reduces the risk of missing anything sensitive. Finally, the software allows for selective encryption or redaction of sensitive sections of the document.
Inside Innovation at Xerox
Xerox researchers, scientists and engineers conduct work in color science, computing, digital imaging, work practices, electromechanical systems, novel materials, and other disciplines connected to Xerox's expertise in printing and document management. A recipient of the National Medal of Technology, the highest technology award in the United States, for its innovations, the company consistently builds its inventions into business by embedding them in Xerox products and solutions, using them as the foundation for new business, or licensing or selling them to other entities. For more information, visit www.xerox.com/innovation.
PARC, a Xerox Corporation company, collaborates with sponsors and clients to discover breakthrough business and technology concepts that solve real needs, and transform how enterprises deliver value to customers. Founded in 1970 as part of Xerox Research, then incorporated in 2002 as an independent research business, PARC is celebrated for innovations such as laser printing, distributed computing and Ethernet, the graphical user interface (GUI), object-oriented programming, and ubiquitous computing. For more information, visit www.parc.com.
Watch Redaction demo (WMV 7.8MB)
Linda Jacobson, Manager, Communications & Marketing