Symantec Integrates Machine Learning Into DLP

Vector Machine Learning is designed to overcome the limitations of current detection technologies

December 14, 2010

6 Min Read


MOUNTAIN VIEW, Calif. – Dec. 14, 2010 – Symantec Corp. (Nasdaq: SYMC) today announced it will offer Symantec Data Loss Prevention 11, which will focus on simplifying the detection and protection of enterprises’ most valuable information – their intellectual property. This major new release of Symantec’s market-leading data security suite plans to feature Vector Machine Learning, the market's first and only machine learning technology, designed to simplify the detection of hard-to-find intellectual property. Symantec Data Loss Prevention 11 is also expected to make the remediation process more efficient and effective with new Data Insight enhancements and to include additional security measures at the endpoint.

Click to Tweet: Symantec DLP simplifies the detection and protection of intellectual property and other sensitive data:

More Data, More Risk

Unstructured data is growing at a rate of more than 60 percent[1] per year and is becoming increasingly difficult to manage and protect. An organization’s most valuable information – its intellectual property – is often buried within a growing volume of unstructured documents, many of which are not sensitive. Unstructured data stores are also typically less secure than other data repositories, making them more vulnerable to data loss from both internal and external threats. As evidenced by targeted attacks such as Hydraq and other high profile losses of confidential documents, intellectual property is more vulnerable than ever before.

Easier to Identify with Vector Machine Learning

An organization needs to identify its sensitive documents before it can take steps to protect them. Data loss prevention has historically relied on two categories of detection technology: fingerprinting and describing the information. Fingerprinting requires collecting all the documents that need to be protected and assigning unique fingerprints to each file. The alternative, describing the data, involves the creation of regular expressions and keyword lists to identify sensitive documents. Fingerprinting can be challenging for organizations with widely dispersed data, and policies to describe data can be both time consuming to create and less accurate than fingerprinting.

Vector Machine Learning is a new innovation from Symantec which is designed to overcome the limitations of current detection technologies. Vector Machine Learning can be trained using sample documents to recognize the defining characteristics and identify the subtle differences between sensitive and non-sensitive data. This will eliminate the need to create keyword-based policies or try to fingerprint new documents as they are created. Vector Machine Learning is designed to allow a sample set of documents to be sufficient to create an accurate policy, and for its accuracy to be improved over time as additional positive and negative samples are fed back into the system.

Easier to Fix with Data Insight Enhancements

Symantec Data Loss Prevention 11 plans to include enhancements to Symantec Data Insight which will streamline the remediation process by identifying the locations where data is at the greatest risk and automatically notifying the associated data owners. The new Risk Scoring feature will prioritize folders for remediation based on the amount and sensitivity of data they contain as well as the folder’s accessibility. The new Data Owner Remediation capability will help facilitate data security awareness and protection by automatically sending email alerts to owners of the data at risk in shared storage, thereby increasing the effectiveness of an organization’s data protection initiatives.

Added Protection at the Endpoint

Symantec Data Loss Prevention 11 is expected to deliver multiple endpoint enhancements, including features designed to give organizations the flexibility to allow the use of a wider range of applications and storage devices while maintaining a strong data security posture. Application File Access Control is designed to ensure user-driven applications such as iTunes, Skype and WebEx can be used by employees without exposing sensitive data. The Trusted Devices feature will enable the use of a wide range of storage devices while assuring that sensitive data can be copied only to approved devices, such as devices issued and tracked by the company. Also new in this release is Endpoint FlexResponse, which is designed to make it easier for customers to extend data protection at the endpoint by integrating other Symantec and third party solutions, such as encryption and Enterprise Rights Management (ERM).

Supporting Quotes

"Continental Airlines is particularly interested in Risk Scoring and Data Owner Remediation features of Symantec Data Loss Prevention 11—with them, we expect to reduce the time it takes to locate and secure our confidential data. We have found that our ability to engage users in protecting their sensitive data is key to success, and this solution can help us with this objective,” said Cynthia Soares, Senior Manager, Information Security, Continental Airlines. "The ability to automatically monitor the status and health of our sensitive information stores will translate into significant cost benefits.”

“Symantec’s Vector Machine Learning technology will anticipate newly created sensitive data based on machine learning capabilities and dramatically improves an organization’s ability to protect unstructured data,” said Jon Oltsik, principal analyst, Enterprise Strategy Group. ”This is designed to enable organizations to more easily define, detect, and ultimately protect their intellectual property.”

“Symantec Data Loss Prevention 11 is focused on helping Information Security professionals to more efficiently and effectively protect the organization’s most sensitive information,” said Aaron Aubrecht, senior director, product management, Symantec Corporation. “We’ve heard from our customers that more accurate detection of intellectual property and risk-based prioritization of their actions are fundamental elements of an effective information protection program. Our Vector Machine Learning technology and Data Insight enhancements directly address those needs.”


Symantec Data Loss Prevention 11 is scheduled to be available in the first half of 2011.


* Presentation on SlideShare * White Paper: Machine Learning Sets New Standard for Data Loss Prevention: Describe, Fingerprint, Learn (PDF) * Blog Entry: Defending Against Threats to Intellectual Property * Box Shot: Symantec Data Loss Prevention 11 * Infograph: Why is Data Loss Prevention a Top Security Initiative?

Connect with Symantec

* Follow Symantec on Twitter * Join Symantec on Facebook * Symantec Connect Business Community

About Symantec Data Loss Prevention

Symantec Data Loss Prevention delivers a proven, content-aware solution to discover, monitor, protect and manage confidential data wherever it is stored or used. It allows you to measurably reduce your risk of a data breach, demonstrate regulatory compliance and safeguard customer privacy, brand equity and intellectual property.

About Symantec

Symantec is a global leader in providing security, storage and systems management solutions to help consumers and organizations secure and manage their information-driven world. Our software and services protect against more risks at more points, more completely and efficiently, enabling confidence wherever information is used or stored. More information is available at

Keep up with the latest cybersecurity threats, newly discovered vulnerabilities, data breach information, and emerging trends. Delivered daily or weekly right to your email inbox.

You May Also Like

More Insights