PALO ALTO, Calif.--(BUSINESS WIRE)--PARC, a Xerox Company, today announced that it is currently helping the United States government proactively identify internal threats before damaging acts are carried out via a two year, $3.5 million contract with the Department of Defense. Developed via PARC’s open innovation model aimed at commercializing emerging technology quickly and successfully, this technology will first be developed for the U.S. government, but the core technology has the potential to be deployed commercially to help stop corporate insider threats and make inroads in fraud detection in the near future.
“PARC has a long track record of working with government agencies – and a network of commercial and other partners – to make important technological advancements that benefit all of our lives,” said Stephen Hoover, CEO, PARC. “Open innovation is all about taking powerful ideas and being able to nimbly bring these ideas to commercial fruition. We are pleased to continue working with governmental organizations such as the Department of Defense to bring about change not only for their areas of expertise, but also for our broader society’s good.”
There is a longstanding problem of threats coming from inside government and large organizations where respected employees become malicious, giving away confidential information (e.g., WikiLeaks) or even harming co-workers. While these threats happen seemingly without advance notice and cause severe consequences, there is often a pattern or trail before the fact – a trail that could be traced and uncovered.
Current attempts to stop inside threats have faced several challenges: enormous amounts of data that need to be analyzed in a timely manner; too many false positives using purely structural-anomaly detection; and a lack of automatic semantic interpretation of the data at hand. PARC researchers are working on the answer to this problem through its work on the Defense Advanced Research Projects Agency (DARPA)’s ADAMS (Anomaly Detection At Multiple Scales) program. Specifically, PARC is involved in spearheading the Graph Learning for Anomaly Detection using Psychological Context (GLAD-PC) project, which aims to provide automatic, proactive threat identification and ranking from large-scale behavioral and information-network datasets.
PARC was chosen for the contract because of its: unique qualifications translating research to actionable insight; established expertise in machine learning and anomaly detection, psychological modeling, ethnography, and social network analysis; and experience analyzing very large-scale (terabyte) datasets. Given its partnership model, PARC has selected a number of subcontractors to complement its core capabilities for this particular government project. On the psychological context modeling and analysis side, HumRRO is providing expertise in dynamic psychological modeling, the psychology of insider attacks, and the connection between personality traits and behavior. On the graph learning side, NASA Ames Research Center is providing unique capabilities in graph structure analysis and anomaly detection. Well known for research in semantic information network analysis and graph theory, Stony Brook University is also contributing to the project.
About PARC
PARC, a Xerox company, is in the Business of Breakthroughs®. Practicing open innovation, we provide custom R&D services, technology, expertise, best practices, and intellectual property to Fortune 500 and Global 1000 companies, startups, and government agencies and partners. We create new business options, accelerate time to market, augment internal capabilities, and reduce risk for our clients.
Since its inception, PARC has pioneered many technology platforms – from the Ethernet and laser printing to the GUI and ubiquitous computing – and has enabled the creation of many industries. Incorporated as an independent wholly owned subsidiary of Xerox in 2002, PARC today continues the research that enables breakthroughs for our clients' businesses.
Engage with PARC on Twitter @parcinc, on our blog, and at our Slideshare channel, as well as subscribe to e-newsletters and more at www.parc.com/updates.