U.S. intelligence agencies use semantic analysis software to find potential security threats from massive volumes of incoming data.
Spy Tech: 10 CIA-Backed Investments
(click image for larger view and for slideshow)
The planning that led up to last week's terrorist attacks in Boston is still largely a mystery, although more details are slowly becoming known. The fact that the Boston Marathon bombings occurred, however, show the daunting challenges that military and law enforcement officials face in preventing terrorist attacks.
U.S. military intelligence analysts regularly sift through vast and varied data sets, including a big data-style mash-up of email, cellphone records, newspaper articles, video clips and audio snippets of phone conversations.
One way to simplify this painstaking process is via software that uses machine-learning technology and semantic analysis algorithms. These tools can help analysts, who may be deluged by too much data, by using detailed graphs and other visualization features to make massive volumes of information easier to study.
Modus Operandi, a Melbourne, Fla., software company that primarily serves the U.S. military and intelligence community, specializes in tools that combine semantic capabilities with defense sector systems.
The company has been around for nearly three decades, but 10 years ago it began focusing on semantic technology -- very simply put, tagging and describing data -- and applying it to what's now referred to as big data analytics. Semantic tags give meaning to unstructured data, thereby making it easier for computers and humans to understand it.
In a phone interview with InformationWeek, Modus Operandi president Richard McNeight and VP and chief scientist Dr. Eric Little discussed the complexities of managing disparate military databases, and how semantic technology can help intelligence analysts find critical information quickly.
Modus Operandi's Wave Exploitation Framework (Wave-EF), for instance, is a product suite that identifies and tags concepts and relationships in unstructured data. It feeds this information to analysts' tools for correction and visualization. The company's software also allows analysts to explore data via a semantic wiki.
"The analyst is looking for something very specific -- a place, person, time or event," said McNeight. "It's very difficult to search and parse that document and determine if it matches the (analyst's) search criteria."
Data graphs are also essential to presenting varied information in an easy-to-understand manner.
"When we take in this raw data, we build models around (it), and these models are called ontologies," said Dr. Little. "The ontologies capture entities and relationships, and allow you to build things into (data) graphs."
Graphical presentation of large data sets, often via maps, diagrams, or other visual tools, is a good way to reduce complexity. "It allows your average user to quickly see things they wouldn't have been able to," said Dr. Little, who added that traditional means of analysis, such as manually scanning multiple spreadsheets or documents, are far less effective.
For national security reasons, Modus Operandi officials were unable to reveal specific details of how intelligence agents use their software. However, McNeight did say the U.S. Air Force is using one of the company's applications to analyze email. "It's fully deployed on a 24/7 basis," he noted.
In addition, Modus Operandi is involved in joint exercises with the U.S. Army and Marine Corps to evaluate and improve its big data tools. And the U.S. Navy is testing the company's software with a mix of data types, including full motion video, provided by other tech vendors.
"There may be eight to 10 other companies that we work with, and we're working to integrate their data streams into our semantic wiki," said McNeight.
Big data presents an intriguing challenge for military intelligence, particularly with the rapid growth of machine sensors generating lots of information.
"The more data we have out there, the harder it is to find anything useful," said Dr. Little. "So a lot of what we're aiming our gun barrels at here has to do with the problem of scalability of these systems over different kinds of heterogeneous data."
Attend Interop Las Vegas, May 6-10, and learn the emerging trends in information risk management and security. Use Priority Code MPIWK by April 29 to save an additional $200 off All Access and Conference Passes. Join us in Las Vegas for access to 125+ workshops and conference classes, 300+ exhibiting companies, and the latest technology. Register for Interop today!
6 Tools to Protect Big DataMost IT teams have their conventional databases covered in terms of security and business continuity. But as we enter the era of big data, Hadoop, and NoSQL, protection schemes need to evolve. In fact, big data could drive the next big security strategy shift.
Big Data Brings Big Security ProblemsWhy should big data be more difficult to secure? In a word, variety. But the business won’t wait to use it to predict customer behavior, find correlations across disparate data sources, predict fraud or financial risk, and more.
InformationWeek Must Reads Oct. 21, 2014InformationWeek's new Must Reads is a compendium of our best recent coverage of digital strategy. Learn why you should learn to embrace DevOps, how to avoid roadblocks for digital projects, what the five steps to API management are, and more.