Innovation @ HP Labs

Insights on research, innovation, and emerging technology from HP Labs researchers around the world.

Learn more at www.hpl.hp.com

HP Discover Barcelona – Pratyusa Manadhata offers “A Sneak Peek at Big Data for Security Research”

Contributed by Simon First, freelance technology writer

 

10june2013_hpdiscover_03349.jpg

 

Pratyusa Manadhata.jpgHow can we harness Big Data to create a new generation of truly scalable enterprise security services? That’s the subject of a December 11th presentation at HP Discover 2013 in Barcelona by HP Labs security researcher Pratyusa K. Manadhata.

 

Current approaches to enterprise security typically look only for known indicators from previous attacks. But some of the most dangerous assaults on enterprise IT systems don’t reveal any such markers until it’s too late.

 

“A way around that is to look for evidence of suspicious activity within the total set of events that occur on a network,” says Manadhata. “But the practical challenge is vast. We estimate that HP alone generates about 1 trillion network events every day. That’s about 12 million every second.”

 

Simply collecting and storing that volume of data, let alone analyzing it effectively to uncover evidence of an attack in progress – especially when you don’t know exactly what to look for – is beyond the capabilities of modern security systems. But as enterprises become more adept at collecting and analyzing data across their business, Manadhata believes, they can use that expertise to drive improvements in analytics for security.

 

“The vision is that we’ll design algorithms and build systems that can collect all this data, store them, analyze them in real time to find novel attacks and then present the results to analysts in a way that they can act on them,” he suggests.

 

But the first step, says Manadhata, is to properly frame the problem. “We need to agree on what we mean by Big Data analysis for security, and why it can be useful. Then we can establish what the hard problems are and begin to try and resolve them,” he says.

 

In his Discover presentation, Manadhata will explore how those questions might be answered – and he’ll discuss several real-world examples where HP researchers have successfully identified security-relevant information within very large enterprise datasets.

                                                                                                   

Based in Princeton, New Jersey, Manadhata is a member of HP’s Security and Cloud Lab. Before joining HP in 2011, he studied for his PhD in computer science at Carnegie Mellon University and was a researcher at Symantec Research Labs in Los Angeles, where he designed and built Big Data analytics systems for malware detection. He co-leads the Cloud Security Alliance’s subgroup on Big Data analytics for security and regularly speaks on the topic, including the Heidelberg Laureate Forum.

 

Discover attendees can attend Manadhata’s talk on Wednesday, December 11th, at 10:40 AM. Click here for information about other HP Discover sessions being presented by HP Labs researchers in Barcelona. HP Labs executives will also available at the HP on HP and HP Labs Guru Bar throughout the event for one-on-one conversations. 

 

 

Leave a Comment

We encourage you to share your comments on this post. Comments are moderated and will be reviewed
and posted as promptly as possible during regular business hours

To ensure your comment is published, be sure to follow the community guidelines.

Be sure to enter a unique name. You can't reuse a name that's already in use.
Be sure to enter a unique email address. You can't reuse an email address that's already in use.
Type the characters you see in the picture above.Type the words you hear.
Search
About the Author


Follow Us
The opinions expressed above are the personal opinions of the authors, not of HP. By using this site, you accept the Terms of Use and Rules of Participation