Search NASA⌕ Search

Engineering topics

Chikkagoudar, Satish

Publications and source records attributed to Chikkagoudar, Satish.

Collaboration and Negotiation

Collaboration and Negotiation is a critical high-level function of an Autonomous Intelligent Cyber-Defense Agent (AICA) that enables communication among agents, central cyber C2, and human operators. Maintaining the Confidentiality, Integrity, and Availability (CIA) triad while achieving mission goals requires stealthy AICA agents to exercise: 1) minimal communication as needed for avoiding detection, 2) verification of information received with possibly limited resources, and 3) active learning during operations to address dynamic conditions. Moreover, negotiations to jointly identify and execute a Course of Action (COA) solution will require building consensus under distributed and/or decentralized multiagent settings with information uncertainties. This chapter presents algorithmic approaches for enabling the collaboration and negotiation function. Strengths and limitations of potential techniques are identified, and a representative example is illustrated. Recommendations for future development are also discussed.

Chatterjee, Samrat↗

Assurance by Design for Cyber Physical Data-Driven Systems

Currently, Cyber Physical Data-Driven Systems (CPDDS) employ machine learning for the classification, data fusion, and control of our nation’s infrastructure, such as the power grid, transportation networks (e.g., fuel distribution, air traffic control), and DoD long-duration collaborative autonomous platforms including unmanned underwater, ground, surface, space, and aerial systems. Many CPDDSs are system-of-systems that should be designed to communicate over disadvantaged networks. It is important to assure that the CPDDSs are resilient against physical and cyber threats by design. Additionally, their design should tolerate misclassification errors resulting from natural and/or adversarial distribution shifts within their data driven components. The all-domain nature of the problem of assuring the design of CPDDSs requires a multi-disciplinary perspective as outlined in this chapter.

Chikkagoudar, Satish↗

Extracting dependencies between network assets using deep learning

A network analysis tool receives network flow information and uses deep learning—machine learning that models high-level abstractions in the network flow information—to identify dependencies between network assets. Based on the identified dependencies, the network analysis tool can discover functional relationships between network assets. For example, a network analysis tool receives network flow information, identifies dependencies between multiple network assets based on evaluation of the network flow information, and outputs results of the identification of the dependencies. When evaluating the network flow information, the network analysis tool can pre-process the network flow information to produce input vectors, use deep learning to extract patterns in the input vectors, and then determine dependencies based on the extracted patterns. The network analysis tool can repeat this process so as to update an assessment of the dependencies between network assets on a near real-time basis.

Carroll, Thomas E.↗

Complementary workflows for identifying one-hop network behavior and multi-hop network dependencies

A network analysis tool evaluates network flow information in complementary workflows to identify one-hop behavior of network assets and also identify multi-hop dependencies between network assets. In one workflow (e.g., using association rule learning), the network analysis tool can identify significant one-hop communication patterns to and/or from network assets, taken individually. Based on the identified one-hop behavior, the network analysis tool can discover patterns of similar communication among different network assets, which can inform decisions about deploying patch sets, mitigating damage, configuring a system, or detecting anomalous behavior. In a different workflow (e.g., using deep learning or cross-correlation analysis), the network analysis tool can identify significant multi-hop communication patterns that involve network assets in combination. Based on the identified multi-hop dependencies, the network analysis tool can discover functional relationships between network assets, which can inform decisions about configuring a system, managing critical network assets, or protecting critical network assets.

97 MATHEMATICS AND COMPUTING↗

Automating Network Node Behavior Characterization by Mining Communication Patterns

Enterprise networks of scale are complex, dynamic computing environments that respond to evolv- ing business objectives and requirements. Characteriz- ing system behaviors in these environments is essential for network management and cyber security operations. Characterization of system’s communication is typical and is supported using network flow information (NetFlow). Related work has characterized behavior using theoretical graph metrics; results are often difficult to interpret by enterprise staff. We propose a different approach, where flow information is mapped to sets of tags that contextualize the data in terms of network principals and enterprise concepts. Frequent patterns are then extracted and are expressed as behaviors. Behaviors can be com- pared, identifying systems expressing similar behaviors. We evaluate the approach using flow information collected by a third party.

cyber system modeling↗

Machine Learning

The absence of a robust and unified theory of cyber dynamics presents challenges and opportunities for using machine learning based data-driven approaches to further the understanding of the behavior of such complex systems. Analysts can also use machine learning approaches to gain operational insights. In order to be operationally beneficial, cybersecurity machine learning based models need to have the ability to: (1) represent a real-world system, (2) infer system properties, and (3) learn and adapt based on expert knowledge and observations. Probabilistic models and Probabilistic graphical models provide these necessary properties and are further explored in this chapter. Bayesian Networks and Hidden Markov Models are introduced as an example of a widely used data driven classification/modeling strategy.

Anomaly detection↗

Impact of Network Activity Levels on the Performance of Passive Network Service Dependency Discovery

Network services often do not operate alone, but instead, depend on other services distributed throughout a network to correctly function. If a service fails, is disrupted, or degraded, it is likely to impair other services. The web of dependencies can be surprisingly complex---especially within a large enterprise network---and evolve with time. Acquiring, maintaining, and understanding dependency knowledge is critical for many network management and cyber defense activities. While automation can improve situation awareness for network operators and cyber practitioners, poor detection accuracy reduces their confidence and can complicate their roles. In this paper we rigorously study the effects of network activity levels on the detection accuracy of passive network-based service dependency discovery methods. The accuracy of all except for one method was inversely proportional to network activity levels. Our proposed cross correlation method was particularly robust to the influence of network activity. The proposed experimental treatment will further advance a more scientific evaluation of methods and provide the ability to determine their operational boundaries.

correlation↗

Disentangling the Lexicons of Disaster Response in Twitter

Abstract: People around the world use social media platforms such as Twitter heavily to express their opinion about various as- pects of daily life. In the same way social media changes communication in daily life, it also is transforming the way individuals communicate during disasters and emergencies. Emergency officials have come to rely on social media to communicate alerts and updates. How do users communi- cate risk on social media? We used a novel information- theoretic unsupervised learning tool, CorEx, to extract and classify highly relevant words used by the public on Twit- ter during known emergencies, such as fires, explosions, and hurricanes. By utilizing the resulting classification strategy, authorities can use the derived language to craft more rel- evant risk communication to maximize the effectiveness of short-message broadcasts such as the Wireless Emergency Alerts (WEA) service.

clustering↗

Comparative hazard analysis and toxicological modeling of diverse nanomaterials using the embryonic zebrafish (EZ) metric of toxicity

The integration of rapid assays, large data sets, informatics and modeling can overcome current barriers in understanding nanomaterial structure-toxicity relationships by providing a weight-of-the-evidence mechanism to generate hazard rankings for nanomaterials. Here we present the use of a rapid, low-cost assay to perform screening-level toxicity evaluations of nanomaterials in vivo. Calculated EZ Metric scores, a combined measure of morbidity and mortality, were established at realistic exposure levels and used to develop a predictive model of nanomaterial toxicity. Hazard ranking and clustering analysis of 68 diverse nanomaterials revealed distinct patterns of toxicity related to both core composition and outermost surface chemistry of nanomaterials. The resulting clusters guided the development of a predictive model of gold nanoparticle toxicity to embryonic zebrafish. In addition, our findings suggest that risk assessments based on the size and core composition of nanomaterials alone may be wholly inappropriate, especially when considering complex engineered nanomaterials. These findings reveal the need to expeditiously increase the availability of quantitative measures of nanomaterial hazard and broaden the sharing of that data and knowledge to support predictive modeling. In addition, research should continue to focus on methodologies for developing predictive models of nanomaterial hazard based on sub-lethal responses to low dose exposures.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

SIGNATURES OF ILLICIT NUCLEAR PROCUREMENT NETWORKS: AN OVERVIEW OF PRELIMINARY APPROACHES AND RESULTS

The illicit trafficking of strategic nuclear commodities (defined here as the goods needed for a covert nuclear program excluding special nuclear materials) poses a significant challenge to the international nuclear nonproliferation community. Export control regulations, both domestically and internationally, seek to inhibit the spread of strategic nuclear commodities by restricting their sale to parties that may use them for nefarious purposes. However, export controls alone are not sufficient for preventing the illicit transfer of strategic nuclear goods. There are two major pitfalls to relying solely on export control regulations for the deterrence of proliferation of strategic goods. First, export control enforcement today relies heavily on the honesty and willingness of participants to adhere to the legal framework already in place. Secondly, current practices focus on the evaluation of single records which allow for the necessary goods to be purchased separately and hidden within the thousands of legitimate commerce transactions that occur each day, disregarding strategic information regarding several purchases. Our research presents two preliminary data-centric approaches for investigating procurement networks of strategic nuclear commodities. Pacific Northwest National Laboratory (PNNL) has been putting significant effort into nonproliferation activities as an institution, both in terms of the classical nuclear material focused approach and in the examination of other strategic goods necessary to implement a nuclear program. In particular, the PNNL Signature Discovery Initiative (SDI) has codified several scientific methodologies for the detection, characterization, and prediction of signatures that are indicative of a phenomenon of interest. The methodologies and tools developed under SDI have already been applied successfully to problems in bio-forensics, cyber security and power grid balancing efforts and they have now made the nonproliferation of strategic goods into a challenge problem for testing their methodology and tools. As a first step towards the detection and characterization of illicit procurement networks, our research examines procurement networks as defined by a system of entities (people or companies) that enter into transactions of specific items with one another. Once we have defined such networks, we are interested in answering questions about the behavior and characterization of such networks. The questions we wish to answer regarding procurement networks are, first, “Can we detect networks within large, noisy datasets?” and second, “To what extent can we compare multiple networks and identify their similarities?” As procurement networks can be naturally viewed as a graph, we have employed several graph analytic tools to aid in these tasks. In particular, Graphscape, an SDI tool, uses a novel method to approximate edit distance, a graph distance measure based on the number of changes needed to transform one graph into another, in order to measure how similar two given graphs are to each other. Given a set of graphs where vertices represent companies and edges represent a shipment from company A to company B, we can calculate an all-for-all comparison of graphs. In this way, we are able to determine which graphs are most similar, and which require more changes to transform one into the other. The set of graphs to be compared can be further specialized to provide more insight, e.g., using different time periods to explore events in a company life cycle.

graph analysis↗

Physicochemical signatures of nanoparticle-dependent complement activation

Nanoparticles are potentially powerful therapeutic tools that have the capacity to target drug payloads and imaging agents. However, some nanoparticles can activate complement, a branch of the innate immune system, and cause adverse side-effects. Recently, we developed an in vitro hemolytic assay protocol for measuring the nanoparticle-dependent complement activity of serum samples and applied this protocol to several nanoparticle formulations that differed in size, surface charge, and surface chemistry; quantifying the nanoparticle-dependent complement activity using a metric called Residual Hemolytic Activity (RHA). In the present work, we have used a decision tree learning algorithm to derive the rules for estimating nanoparticle-dependent complement response based on the data generated from the hemolytic assay studies. Our results indicate that physicochemical properties of nanoparticles, namely, size, polydispersity index, zeta potential, and mole percentage of the active surface ligand of a nanoparticle, can serve as good descriptors for prediction of nanoparticle-dependent complement activation in the decision tree modeling framework. The robustness and predictability of the model can be improved by training the model with additional data points that are uniformly distributed in the RHA/physicochemical descriptor space and by incorporating instability effects on nanoparticle physicochemical properties into the model.

informatics↗

Automated Detection of Anomalous Shipping Manifests to Identify Illicit Trade

We describe an approach to analyzing trade data which uses clustering to detect similarities across shipping manifest records, classification to evaluate clustering results and categorize new unseen shipping data records, and visual analytics to provide to support situation awareness in dynamic decision making to monitor and warn against the movement of radiological threat materials through search, analysis and forecasting capabilities. The evaluation of clustering results through classification and systematic inspection of the clusters show the clusters have strong semantic cohesion and offer novel ways to detect transactions related to nuclear smuggling.

classification↗

A Formal Model for Real-Time Parallel Computation

The imposition of real-time constraints on a parallel computing environment--- specifically high-performance, cluster-computing systems--- introduces a variety of challenges with respect to the formal verification of the system's timing properties. In this paper, we briefly motivate the need for such a system, and we introduce an automaton-based method for performing such formal verification. We define the concept of a consistent parallel timing system: a hybrid system consisting of a set of timed automata (specifically, timed Buechi automata as well as a timed variant of standard finite automata), intended to model the timing properties of a well-behaved real-time parallel system. Finally, we give a brief case study to demonstrate the concepts in the paper: a parallel matrix multiplication kernel which operates within provable upper time bounds. We give the algorithm used, a corresponding consistent parallel timing system, and empirical results showing that the system operates under the specified timing constraints.

formal methods↗

Towards Real-Time High Performance Computing For Power Grid Analysis

Real-time computing has traditionally been considered largely in the context of single-processor and embedded systems, and indeed, the terms real-time computing, embedded systems, and control systems are often mentioned in closely related contexts. However, real-time computing in the context of multinode systems, specifically high-performance, cluster-computing systems, remains relatively unexplored. Imposing real-time constraints on a parallel (cluster) computing environment introduces a variety of challenges with respect to the formal verification of the system's timing properties. In this paper, we give a motivating example to demonstrate the need for such a system--- an application to estimate the electromechanical states of the power grid--- and we introduce a formal method for performing verification of certain temporal properties within a system of parallel processes. We describe our work towards a full real-time implementation of the target application--- namely, our progress towards extracting a key mathematical kernel from the application, the formal process by which we analyze the intricate timing behavior of the processes on the cluster, as well as timing measurements taken on our test cluster to demonstrate use of these concepts.

High performance computing, real-time-computing, p↗

Towards a Real-Time Cluster Computing Infrastructure

Real-time computing has traditionally been considered largely in the context of single-processor and embedded systems, and indeed, the terms real-time computing, embedded systems, and control systems are often mentioned in closely related contexts. However, real-time computing in the context of multinode systems, specifically high-performance, cluster-computing systems, remains relatively unexplored, largely due to the fact that until now, there has not been a need for such an environment. In this paper, we motivate the need for a cluster computing infrastructure capable of supporting computation over large datasets in real-time. Our motivating example is an analytical framework to support the next generation North American power grid, which is growing both in size and complexity. With streaming sensor data in the future power grid potentially reaching rates on the order of terabytes per day, the task of analyzing this data subject to real-time guarantees becomes a daunting task which will require the power of high-performance cluster computing capable of functioning under real-time constraints. One specific challenge that such an environment presents is the need for real-time networked communication between cluster nodes. In this paper, we discuss the need for real-time high-performance cluster computation, along with our work-in-progress towards an infrastructure which will ultimately enable such an environment.

99 GENERAL AND MISCELLANEOUS↗