Publications

Results 43801–43900 of 99,299

Search results

Jump to search filters

Using Machine Learning in Adversarial Environments

Davis, Warren L.

Intrusion/anomaly detection systems are among the first lines of cyber defense. Commonly, they either use signatures or machine learning (ML) to identify threats, but fail to account for sophisticated attackers trying to circumvent them. We propose to embed machine learning within a game theoretic framework that performs adversarial modeling, develops methods for optimizing operational response based on ML, and integrates the resulting optimization codebase into the existing ML infrastructure developed by the Hybrid LDRD. Our approach addresses three key shortcomings of ML in adversarial settings: 1) resulting classifiers are typically deterministic and, therefore, easy to reverse engineer; 2) ML approaches only address the prediction problem, but do not prescribe how one should operationalize predictions, nor account for operational costs and constraints; and 3) ML approaches do not model attackers’ response and can be circumvented by sophisticated adversaries. The principal novelty of our approach is to construct an optimization framework that blends ML, operational considerations, and a model predicting attackers reaction, with the goal of computing optimal moving target defense. One important challenge is to construct a realistic model of an adversary that is tractable, yet realistic. We aim to advance the science of attacker modeling by considering game-theoretic methods, and by engaging experimental subjects with red teaming experience in trying to actively circumvent an intrusion detection system, and learning a predictive model of such circumvention activities. In addition, we will generate metrics to test that a particular model of an adversary is consistent with available data.

More Details
TYPE Other Report YEAR 2016
DOIOSTI

Treatment of Oil & Gas Produced Water

Dwyer, Brian P.

Production of oil and gas reserves in the New Mexico Four Corners Region results in large volumes of "produced water". The common method for handling the produced water from well production is re-injection in regulatory permitted salt water disposal wells. This is expensive (%7E $5/bbl.) and does not recycle water, an ever increasingly valuable commodity. Previously, Sandia National Laboratories and several NM small business tested pressure driven membrane-filtration techniques to remove the high TDS (total dissolved solids) from a Four Corners Coal Bed Methane produced water. Treatment effectiveness was less than optimal due to problems with pre-treatment. Inadequate pre-treatment allowed hydrocarbons, wax and biological growth to foul the membranes. Recently, an innovative pre-treatment scheme using ozone and hydrogen peroxide was pilot tested. Results showed complete removal of hydrocarbons and the majority of organic constituents from a gas well production water. ACKNOWLEDGEMENTS This report was made possible through funding from the New Mexico Small Business Administration (NMSBA) Program at Sandia National Laboratories. Special thanks to Juan Martinez and Genaro Montoya for guidance and support from project inception to completion. Also, special thanks to Frank McDonald, the small businesses team POC, for laying the ground work for the entire project; Teresa McCown, the gas well owner and very knowledgeable- fantastic site host; Lea and Tim Phillips for their tremendous knowledge and passion in the oil & gas industry.; and Frank Miller and Steve Addleman for providing a pilot scale version of their proprietary process to facilitate the pilot testing.

More Details
TYPE SAND Report YEAR 2016
DOIOSTI

Environmental Baseline Survey for Proposed Land Use Permit Modification for Expansion of the Dynamic Explosive Test Site (DETS) 9940 Main Complex Parking Lot

Peek, Dennis W.

The approach was to perform a document search, supplemented by a visual site inspection, to identify potential environmental contamination associated with the property. Factors evaluated included hazardous substances; petroleum products and derivatives; environmental restoration sites; areas of concern; storage tanks; oil/water separators; grease traps; wash racks; waste tanks; pesticides; military munitions/ordnance; medical or bio-hazardous waste; radioactive waste; solid/municipal waste; indoor air quality; groundwater; wastewater treatment, collection, and disposal/discharge; drinking water quality; utilities; asbestos; polychlorinated biphenyls (PCBs); radon; lead-based paint; cultural resources; floodplains; and natural/biological resources.

More Details
TYPE Other Report YEAR 2016
DOIOSTI

2014 Annual Site Environmental Report Summary Pamphlet for Sandia National Laboratories New Mexico

Griffith, Stacy

This ASER Summary Pamphlet presents the environmental protection, restoration, and monitoring programs in place at SNL/NM during calendar year 2014. It also discusses Sandia’s compliance with environmental regulations, and it highlights significant environmental program efforts and accomplishments. The environmental programs and waste management activities at SNL/NM meet or exceed the requirements of federal, state, and local environmental regulations, as well as DOE directives in the contract between Sandia and DOE. This document, prepared in accordance with and as required by DOE Order 231.1B, Environment, Safety, and Health Reporting, is a key component of DOE’s efforts to keep the public informed about environmental conditions throughout the DOE/NNSA nuclear weapons complex.

More Details
TYPE Other Report YEAR 2016
DOIOSTI

Digital Image Correlation for Performance Monitoring

Palaviccini, Miguel; Turner, D.Z.; Herzberg, Michael

Evaluating the health of a mechanism requires more than just a binary evaluation of whether an operation was completed. It requires analyzing more comprehensive, full-field data. Health monitoring is a process of nondestructively identifying characteristics that indicate the fitness of an engineered component. In order to monitor unit health in a production setting, an automated test system must be created to capture the motion of mechanism parts in a real-time and non-intrusive manner. One way to accomplish this is by using high-speed video (HSV) and Digital Image Correlation (DIC). In this approach, individual frames of the video are analyzed to track the motion of mechanism components. The derived performance metrics allow for state-of-health monitoring and improved fidelity of mechanism modeling. The results are in-situ state-of-health identification and performance prediction. This paper introduces basic concepts of this test method, and discusses two main themes: the use of laser marking to add fiducial patterns to mechanism components, and new software developed to track objects with complex shapes, even as they move behind obstructions. Finally, the implementation of these tests into an automated tester is discussed.

More Details
TYPE Other Report YEAR 2016
DOIOSTI

Metrics for the Complexity of Material Models

Silling, Stewart

Quantitative measures are proposed for characterizing the complexity of material models used in computational mechanics. The algorithms for evaluating these metrics operate on the mathematical equations in the model rather than a code implementation and are different from software complexity measures. The metrics do not rely on a physical understanding of the model, using instead only a formal statement of the equations. A new algorithm detects the dependencies, whether explicit or implicit, between all the variables. The resulting pattern of dependencies is expressed in a set of pathways, each of which represents a chain of dependence between the variables. These pathways provide the raw data used in the metrics, which correlate with the expected ease of understanding, coding, and applying the model. Usage of the ComplexityMetrics code is described, with examples.

More Details
TYPE SAND Report YEAR 2016
DOIOSTI

WEC-SIM Validation Testing Plan FY14 Q4

Ruehl, Kelley M.

The WEC-Sim project is currently on track, having met both the SNL and NREL FY14 Milestones, as shown in Table 1 and Table 2. This is also reflected in the Gantt chart uploaded to the WEC-Sim SharePoint site in the FY14 Q4 Deliverables folder. The work completed in FY14 includes code verification through code-to-code comparison (FY14 Q1 and Q2), preliminary code validation through comparison to experimental data (FY14 Q2 and Q3), presentation and publication of the WEC-Sim project at OMAE 2014 [1], [2], [3] and GMREC/METS 2014 [4] (FY14 Q3), WEC-Sim code development and public open-source release (FY14 Q3), and development of a preliminary WEC-Sim validation test plan (FY14 Q4). This report presents the preliminary Validation Testing Plan developed in FY14 Q4. The validation test effort started in FY14 Q4 and will go on through FY15. Thus far the team has developed a device selection method, selected a device, and placed a contract with the testing facility, established several collaborations including industry contacts, and have working ideas on the testing details such as scaling, device design, and test conditions.

More Details
TYPE Other Report YEAR 2016
DOIOSTI

Analytic framework for the United States cyber deterrence strategy. Final draft, 2nd submission (20 May 2015]

Jackson, Marian C.; Blackwell, Heather; Mccann, Jennifer

If the United States (U.S.) government allows cyberattacks to continue on their current trajectory of increased frequency and effect, the bonds holding our society together will be jeopardized, potentially impacting the survival of our society as we know it. Actions must be taken not only to defend against, but also to deter future cyberattacks. To achieve a credible and actionable U.S. Cyber Deterrence Strategy, the following three lines of effort are recommended for implementation by the White House: 1. Add a sixth priority to the Obama Administration's current cyberspace priorities to state: "Advance our cyber response policies and capabilities to further protect the country's national interests by deterring attacks within cyberspace." 2. Adopt the proposed Cyber Deterrence Analytic Framework as a guide for policy makers to use when determining the appropriate response to a cyberattack. 3. Implement the proposed Presidential Policy Directive outlining the United States' deterrence policy for cyber. These recommendations for establishing a U.S. Cyber Deterrence Strategy address the following key findings: As the U.S. private sector owns and operates over 90% of all of the networks and infrastructure of cyberspace, an effective policy must be communicated clearly across the government, business enterprise, and most importantly, to the people; More so than any time in our nation's history, individuals, companies, and organizations depend on cyberspace for uses ranging from social interactions to sustaining democracy; Threats existing within the cyber domain have grown both in attack vector complexity and societal impact; and, The current Presidential Executive Orders and Policy Directives related to cyber deterrence do not include a strategy for deterring attacks. The concepts presented in this paper were derived from interviews with experts in subjects ranging from deterrence philosophy, nuclear weapons implementation, U.S. cyber operations, and U.S. cyber policy. In addition, theories on deterrence strategies are explored, ranging from the 1960s to present to develop a deterrence strategy unique to cyber. Lastly, recent examples of cyberattacks are examined to provide evidence for the need to establish consequences for those individuals or countries that continue to behave nefariously within cyberspace. To form a strong foundation for a U.S. Cyber Deterrence Strategy, the U.S. must establish and clearly articulate the consequences for nations or individuals if they choose to initiate a cyberattack on the U.S. or its national interests.

More Details
TYPE Other Report YEAR 2016
DOIOSTI
Results 43801–43900 of 99,299
Results 43801–43900 of 99,299