Dark Reading is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Risk

DoD Taps PARC To Help Detect Insider Threats

PARC, famous for its innovations, will develop technology for the Department of Defense that aims to identify inside security threats, using behavioral data, social networks, and other sources.

Slideshow: Next Generation Defense Technologies
Slideshow: Next Generation Defense Technologies
(click for larger image and for full slideshow)
The Department of Defense (DoD) has tapped PARC to create technology that can automatically identify the possibility of a security threat coming from inside the department's network.

PARC, which is owned by Xerox, is spearheading a new effort called the Graph Learning for Anomaly Detection using Psychological Context (GLAD-PC). The project will leverage large-scale behavioral data sets as well as information from social networks and other sources to determine when someone inside the military could pose a security risk.

GLAD-PC is a sub-project within the Defense Advanced Research Project Agency's Anomaly Detection at Multiple Scales (ADAMS) program, which will produce technology that can sift through the behavioral signs that someone might turn on the military or his or her cohorts, and prevent the action before it happens.

The DoD has awarded PARC $3.5 million for its role in the project, and the technology developed could have commercial potential after it's deployed within the government.

[ Anonymous claims responsibility for a recent attack on the CIA's website. Read more at CIA Website Hacked, Struggles To Recover. ]

After last year's Wikileaks debacle--in which military intelligence analyst Bradley Manning was arrested for leaking reams of classified data to the whistleblower site--the DoD's sensitivity to insider threats has intensified. The leak eventually led to an international incident dubbed Cablegate, which called attention to the apparent insecurity of U.S. military networks.

In addition to ADAMS, DARPA also has another project with a similar focus called the Cyber Insider Threat program, or CINDER. That program also aims to detect insider threats before they happen, but takes an approach that assumes systems and networks already have been compromised and seeks to mitigate the damage.

So far, technological attempts to detect insider threats have faced challenges because of the large amounts of data that must be analyzed quickly, according to PARC. Using detection based only on structural anomalies has created too many false positives, and there currently is a lack of technology to automatically interpret data semantically, the company said.

PARC said it was chosen for the job of solving these problems because of its expertise in machine learning and anomaly detection, psychological modeling, ethnography, and social network analysis, as well as its experience in working with and analyzing terabyte-sized data sets.

Because the scope of its work will be complex, however--touching on human psychology, data analysis, anomaly detection, and social network analysis, among other practices--the company also will have subcontracting help, including some from another government agency.

The NASA Ames Research Center will provide graph structure analysis and anomaly detection for the graph learning feature of the technology, while the Human Resources Research Organization (HumRRO) will provide expertise in dynamic psychological modeling, the psychology of insider attacks, and the connection between personality traits and behavior, according to PARC. Stony Brook University, which has experience in semantic information network analysis and graph theory, also is contributing to GLAD-PC.

InformationWeek and InformationWeek Government are conducting a survey on IT security and cybersecurity in U.S. federal government agencies. Upon completion of our survey, you will be eligible to enter a drawing to receive an Apple 16-GB iPad 2. Take our Federal Government Cybersecurity Survey now. Survey ends Feb. 24.

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
COVID-19: Latest Security News & Commentary
Dark Reading Staff 9/25/2020
Hacking Yourself: Marie Moe and Pacemaker Security
Gary McGraw Ph.D., Co-founder Berryville Institute of Machine Learning,  9/21/2020
Startup Aims to Map and Track All the IT and Security Things
Kelly Jackson Higgins, Executive Editor at Dark Reading,  9/22/2020
Register for Dark Reading Newsletters
White Papers
Video
Cartoon
Current Issue
Special Report: Computing's New Normal
This special report examines how IT security organizations have adapted to the "new normal" of computing and what the long-term effects will be. Read it and get a unique set of perspectives on issues ranging from new threats & vulnerabilities as a result of remote working to how enterprise security strategy will be affected long term.
Flash Poll
How IT Security Organizations are Attacking the Cybersecurity Problem
How IT Security Organizations are Attacking the Cybersecurity Problem
The COVID-19 pandemic turned the world -- and enterprise computing -- on end. Here's a look at how cybersecurity teams are retrenching their defense strategies, rebuilding their teams, and selecting new technologies to stop the oncoming rise of online attacks.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2020-15208
PUBLISHED: 2020-09-25
In tensorflow-lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, when determining the common dimension size of two tensors, TFLite uses a `DCHECK` which is no-op outside of debug compilation modes. Since the function always returns the dimension of the first tensor, malicious attackers can ...
CVE-2020-15209
PUBLISHED: 2020-09-25
In tensorflow-lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, a crafted TFLite model can force a node to have as input a tensor backed by a `nullptr` buffer. This can be achieved by changing a buffer index in the flatbuffer serialization to convert a read-only tensor to a read-write one....
CVE-2020-15210
PUBLISHED: 2020-09-25
In tensorflow-lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, if a TFLite saved model uses the same tensor as both input and output of an operator, then, depending on the operator, we can observe a segmentation fault or just memory corruption. We have patched the issue in d58c96946b and ...
CVE-2020-15211
PUBLISHED: 2020-09-25
In TensorFlow Lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, saved models in the flatbuffer format use a double indexing scheme: a model has a set of subgraphs, each subgraph has a set of operators and each operator has a set of input/output tensors. The flatbuffer format uses indices f...
CVE-2020-15212
PUBLISHED: 2020-09-25
In TensorFlow Lite before versions 2.2.1 and 2.3.1, models using segment sum can trigger writes outside of bounds of heap allocated buffers by inserting negative elements in the segment ids tensor. Users having access to `segment_ids_data` can alter `output_index` and then write to outside of `outpu...