Search NASA⌕ Search

Engineering topics

Perumalla, Kalyan

Publications and source records attributed to Perumalla, Kalyan.

At least 19 records

CYVET: A Cyber-Physical Assurance Framework Based on a Semi-Supervised Vetting Approach

The project is designed to directly address the needs described in the Topic Area 4 (“Cybersecurity Verification and Validation”) of the CEDS’19 Research Call. The proposed CYVET system directly addresses the need to elevate the current industry capabilities to verify and validate OT cybersecurity and associated control system infrastructure. Currently, there is a significant gap in the energy sector’s capability in that regard during infrastructure improvement, equipment procurement, and compliance certification. CYVET provides that needed capability. CYVET is device and architecture agnostic and thus broadly applicable across the energy sector. The goal of this project is to develop and deliver a cybersecurity verification and validation framework testing capability to verify and validate OT equipment, software, and the underlying control system architecture. The primary project objectives are (i) Verification: the synthesis and reconciliation of standards and vendor supplied features, (ii) Validation: the generation, execution, and presentation of testing scripts of verified security features, and (3) Demonstration: apply the developed technology capabilities for verification and validation at a relevant end-user facility in the energy sector.

Lopez Jr, Juan↗

Design of a Novel Information System for Semi-Automated Management of Cybersecurity in Industrial Control Systems

There is an urgent need in many critical infrastructure sectors, including the energy sector, for attaining detailed insights into cybersecurity features and compliance with cybersecurity requirements related to their Operational Technology (OT) deployments. Frequent feature changes of OT devices interfere with this need, posing a great risk to customers. One effective way to address this challenge is via a semi-automated cyber-physical security assurance approach, which enables verification and validation of the OT device cybersecurity claims against actual capabilities, both pre- and post-deployment. To realize this approach, this paper presents new methodology and algorithms to automatically identify cybersecurity-related claims expressed in natural language form in ICS device documents. Here, we developed an identification process that employs natural language processing (NLP) techniques with the goal of semi-automated vetting of detected claims against their device implementation. We also present our novel NLP components for verifying feature claims against relevant cybersecurity requirements. The verification pipeline includes components such as automated vendor identification, device document curation, feature claim identification utilizing sentiment analysis for conflict resolution, and reporting of features that are claimed to be supported or indicated as unsupported. Our novel matching engine represents the first automated information system available in the cybersecurity domain that directly aids the generation of ICS compliance reports.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Computer Science Research Needs for Parallel Discrete Event Simulation (PDES)

Historically, scientific computing efforts have demonstrated the clear need for, and effective use of, supercomputing with traditional time-stepped simulations. Nevertheless, there are several areas in the mission spaces of the U.S. Department of Energy and other agencies waiting to tap advanced computing research using a different, discrete event style of modeling, simulation, and analysis. These span a wide spectrum of applications including energy grid resilience, urban planning and policy, transportation science, building technologies, emergency response and planning, environmental impact analysis, computational epidemiology, Internet communications, cyber security, and cyber-physical systems, to name only a few. Even within traditional scientific applications, the role of discrete event modes of execution is increasing in the form of new event-based mathematical solvers such as quantized state integration methods and discrete-continuous hybrid system solvers. Co-design of advanced supercomputing hardware systems is another area that exploits discrete event simulation at its core for effective analyses. Complex systems, entity behaviors and interconnections play a significant role in all these applications, which are mapped to large-scale models with discrete event formulations. To make advancements in all the aforementioned scientific areas, many technical aspects need to be more thoroughly studied and deeply understood in parallel discrete event simulation (PDES). The unique dynamics inherent in a discrete event modeling approach, by their very nature, intersect and influence the entire stack of the computing system, including (a) the unique nature of the instruction sets exercised in PDES workloads without a predominance of high-precision floating point operations, (b) virtual time-constrained multi-threaded execution of many logical processes per processor, (c) extremely variable and difficult to predict network traffic characteristics, (d) interfaces and inter-dependencies with machine learning and artificial intelligence codes at higher software layers, and (e) highly challenging load balancing needs, especially in effectively accounting for accelerated/extremely heterogeneous computing in current and future high-performance computing systems. Efficient and accurate parallel execution of PDES workloads is also dominated by challenges in dealing with their asynchronous concurrency fundamentally present at the model level. Conservative synchronization, optimistic/speculative synchronization, and their hybrid schemes open new questions in fundamental computer science with respect to reversibility of computation and prediction (lookahead) of behaviors inherent within model codes. On the implementation front, there are relatively few scalable, general-purpose parallel discrete event simulators in the world, and even fewer have been studied on emerging hardware platforms. To enable scientific advances using PDES, the research needs in computer science must also be pursued and met in the intersection of the algorithmic and hardware-aware aspects of scalable PDES engines. This report is aimed at capturing a computer science-oriented view of this important area of research in PDES, presenting a sample of important applications with their inherent discrete event technology elements. Needs are outlined in core areas of parallel discrete event research as well as cross-cutting directions in computer science research that positively impact scientific advancements across several important application areas. A selection of priority research opportunities in advanced computing for PDES is identified to serve as reference for key research topics and their order of importance for scientific advancements.

97 MATHEMATICS AND COMPUTING↗

Fast GPU-Based Generation of Large Graph Networks From Degree Distributions

Synthetically generated, large graph networks serve as useful proxies to real-world networks for many graph-based applications. The ability to generate such networks helps overcome several limitations of real-world networks regarding their number, availability, and access. Here, we present the design, implementation, and performance study of a novel network generator that can produce very large graph networks conforming to any desired degree distribution. The generator is designed and implemented for efficient execution on modern graphics processing units (GPUs). Given an array of desired vertex degrees and number of vertices for each desired degree, our algorithm generates the edges of a random graph that satisfies the input degree distribution. Multiple runtime variants are implemented and tested: 1) a uniform static work assignment using a fixed thread launch scheme, 2) a load-balanced static work assignment also with fixed thread launch but with cost-aware task-to-thread mapping, and 3) a dynamic scheme with multiple GPU kernels asynchronously launched from the CPU. The generation is tested on a range of popular networks such as Twitter and Facebook, representing different scales and skews in degree distributions. Results show that, using our algorithm on a single modern GPU (NVIDIA Volta V100), it is possible to generate large-scale graph networks at rates exceeding 50 billion edges per second for a 69 billion-edge network. GPU profiling confirms high utilization and low branching divergence of our implementation from small to large network sizes. For networks with scattered distributions, we provide a coarsening method that further increases the GPU-based generation speed by up to a factor of 4 on tested input networks with over 45 billion edges.

97 MATHEMATICS AND COMPUTING↗

Design Considerations for GPU-based Mixed Integer Programming on Parallel Computing Platforms

Mixed Integer Programming (MIP) is a powerful abstraction in combinatorial optimization that finds real-life application across many significant sectors. The recent proliferation of graphical processing unit (GPU)-based accelerated computing architectures in large-scale parallel computing or supercomputing presents new opportunities as well as challenges in the advancement of MIP solver technology to effectively use the new accelerated computing platforms and scale to large parallel systems. Here, we recount the conventional processor-based strategies and focus on configurations where the most promising intersection lies between parallel MIP solver approaches and the specific strengths of accelerated parallel platforms. We note that the best potential lies in solving problems whose individual matrix sizes (of the linear program relaxation) fit entirely within one accelerator's memory and whose branch-and-bound (or branch-and-cut) trees cannot be fully contained within a small number of computational nodes. Additionally, we identify ideal features of computational linear algebra support on GPU accelerators that would help advance this direction of scalable parallel solution of MIP problems on GPU-based accelerated computing architectures.

Perumalla, Kalyan↗

Smart Semi-Supervised Accumulation of Large Repositories for Industrial Control Systems Device Information

Industrial Control Systems device manufacturers frequently add new features to improve their product performance. Oftentimes, these changes are mainly vendor-driven initiatives, and customers may not be aware of the full impact of these new capabilities on their cybersecurity posture. In the energy sector, this can lead to considerable dissonance between vendor-provided cybersecurity claims and a customer’s responsibility for Operation Technology cybersecurity compliance. Thus, the resulting dynamic verification burden is shifted towards the customer and may pose a significant cybersecurity risk to the energy sector landscape. We found that there is very limited research into cybersecurity auditing for Operational Technology. However, a solution is needed for vetting the vendor-supplied feature claims and their adherence to cybersecurity requirements and standards. We are presently engaged in an effort to develop such a system. This paper demonstrates one vital aspect of this effort in proposing an end-to-end framework to accumulate a large repository of ICS device information for this vetting system, curate the dataset, and conduct extensive processing. This framework is designed to use web scraping, data analytics and Natural Language Processing (NLP) techniques to identify vendor websites, automate the collection of website-accessible documents and automatically derive metadata from them for identification of product documents relevant to the repository. We have found that this automated approach to vendor identification, document extraction into a product repository, and NLP pre-processing is unique and has not been previously presented in the literature. The preliminary work shows that this is feasible and can produce reliable results with minimum supervision. Future work will be built upon this foundation in order to achieve semi-supervised vetting of device technical information – a vital capability for ensuring that vendor-claimed device cybersecurity capabilities match industry requirements.

Ameri, Kimia↗

Trust-but-Verify in Cyber-Physical Systems

Cyber-physical systems span a wide spectrum, from long-lived legacy systems to more modern installations. Trust is an issue that arises across the spectrum, albeit with different variants of goals and constraints. On the one end of the spectrum, legacy systems are characterized by function-based designs in which trust is an implicitly in-built concept -- the operation is historically designed, implemented, and optimized in a benign stance with respect to intended use. On the other end of the spectrum, modern systems are characterized by offerings from manufacturers, vendors, and system installers -- the devices and deployments use a variety of security features that offer promises of increased trust. All along this spectrum of cyber-physical systems, extending trust beyond the traditional cyber portions to the arteries that connect the physical portions to the cyber portions is a major challenge. Here, we identify a Trust-but-Verify approach that spans this spectrum in addressing trust.

Perumalla, Kalyan↗

On the Robustness of Network Community Structure Under Addition of Edges

Communities represent important functional modules in networked systems. A key goal in preserving such communities is understanding their robustness under perturbations. Previous research has studied the impact of node removals and edge removals on the community structure. However, the impact of edge additions on the robustness of the community structure is relatively unknown. Edge additions or false positive edges may simulate measurement errors or external exceptional events that threaten the functionality of networked systems. Here, we study the impact of edge additions on the community structure using Lancichinetti-Fortunato-Radicchi (LFR) benchmark networks. We show that, for a fixed network size, the impact of edge additions is greater on networks with initially weak community structure than on networks with strongly clustered structures. In addition, we find that the perception of the impact is also dependent on the community detection algorithm used to uncover communities. In particular, we found that modularity-based methods such as Leiden and Louvain are less affected than information-theoretic and message passing-based methods such as Infomap and Label Propagation. Our results demonstrate that edge addition can (a) significantly impact the community structure of networks based on their initial conditions, and (b) the perception of the impact is dependent on the community detection algorithm used. We describe limitations, open challenges, and how this methodology can inform the design of resilient networked systems under edge additions.

97 MATHEMATICS AND COMPUTING↗

A Novel Vetting Approach to Cybersecurity Verification in Energy Grid Systems

The cybersecurity auditing for Operation Technology is critical and has been largely missing from the cybersecurity research, especially in the energy sector. In this paper, we present a novel “cybersecurity vetting” approach (CYVET) to the problem of verification and validation of cybersecurity in complex cyber-physical installations underlying modern energy grid systems.

Perumalla, Kalyan↗

Kensor: Coordinated Intelligence from Co-Located Sensors

Internet of Things (IoT) is becoming more pervasive in many installations, including homes, manufacturing plants, and industrial facilities of all kinds. The data that IoT produces is a reflection of usual behavior such as daily routines and scheduled tasks, but also from unexpected behavior due to unintentional or undesirable abnormalities. Here, we focus on achieving coordinated intelligence about normal and abnormal phenomena from multiple sensors that are geographically colocated in close proximity, monitoring and controlling a set of co-located devices. Given a set of co-located sensors, we seek an intelligent approach that would automatically determine the “normal” patterns of behaviors among the correlated sensors. After normal behavior is extracted, later monitoring should detect any deviant variations over time. An example application is an entry monitoring and alert system for facilities such as nuclear reactors, where badge readers, door locks, lights, weight trackers and other co-located sensors at the entry point are collectively tracked. To address this problem, we identify the possible solution approach that can be used to solve its different variants. The implemented model is developed as a combination of rules and Markov Chain methods.

Kotevska, Olivera↗

RL-HEMS: Reinforcement Learning Based Home Energy Management System for HVAC Energy Optimization

Heating, ventilation, and air conditioning (HVAC) is one of the major energy consumers in the residential sector. It is important to be able to monitor and control the energy consumed to provide utility services such as load shaping while satisfying the comfort and economic constraints of the homeowner. The objective of this work is to create the optimal schedule for HVAC operation to reduce the cost while satisfying the home-owner and equipment’s constraints using a model-free Reinforcement Learning (RL)-based optimization. The specific goal is to find the right balance between reducing energy cost, consumption, and customer comfort level. Our research effort addresses this optimization problem using multiple components: the development of initial learning test-bed and implementation of RL techniques on a real home. This will enable the rapid evaluation of the RL techniques and provide an early baseline to train before implementation on site. The RL algorithm is designed to learn the energy use patterns and generate the optimized schedule for HVAC within an acceptable time-interval to satisfy the homeowner’s comfort and minimize the energy usage. Our preliminary results are promising and we have observed a 17% reduction in the total cost and a 15% reduction in the power utilization using our RL-based HVAC model—RL-HEMS.

Kotevska, Olivera↗

Energy Conservation Through Cloned Execution Of Simulations

High-performance computing facilities used for scientific computing draw enormous energy, some of them consuming many megawatt-hours. Saving the energy consumption of computations on such facilities can dramatically reduce the total cost of their operation and help reduce environmental effects. Here, we focus on a way to reduce energy consumption in many ensembles of simulations. Using the method of simulation cloning to exploit parallelism while also significantly conserving the computational and memory requirements, we perform a detailed empirical study of energy consumed on a large supercomputer consisting of hardware accelerator cards (graphical processing units, GPUs). We build on previous insights from mathematical analysis and implementation of cloned simulations that result in computational and memory savings by several orders-of-magnitude. Using instrumentation to track the power drawn by thousands of accelerator cards, we report significant aggregate energy savings from cloned simulations.

Yoginath, Srikanth↗

Detecting Sensors and Inferring their Relations at Level-0 in Industrial Cyber-Physical Systems

While there exist tools and techniques to discover, identify, map, and analyze cyber physical components at higher levels of the cyber space, there is a lack of capabilities to reach down to the sensors at the bottom-most levels, such as levels 0 and 1 of the Purdue Enterprise Reference Model for cyber-physical systems (CPS). Conventional information technology (IT)-based tools reach as far as the network-side of programmable logic controllers, but are inadequate to access and analyze the physical side of the CPS infrastructure that directly interfaces with the actual physical processes and systems. In this paper, we present our research and development efforts aimed at addressing this gap, by building a system called Deep-cyberia (Deep Cyber-Physical System Interrogation and Analysis) that incorporates algorithms and interfaces aimed at uncovering sensors and computing estimates of correlations among them.

Perumalla, Kalyan↗

On the Effectiveness of Recurrent Neural Networks for Live Modeling of Cyber-Physical Systems

Attention to cyber security of cyber-physical systems (CPS) has led to the development of innovative cyber-resilient methodologies to ensure early detection and mitigation of cyber anomalies and threats. The concept of Digital Twin (DT) has recently emerged as one of the approaches to achieve the objective of resilience. In the approach using DT, a software-based live model of a target CPS is used to continuously monitor, surveil and verify the correctness of the target CPS operation. In this paper, we empirically study the effectiveness of Recurrent Neural Network (RNN)-based models as the basis of DT-based resilience. We uncover the important characteristics of an RNN-based solution with experimentation on a lab-scale Canal Lock CPS emulator with live validations and attack scenarios. For the first time, we demonstrate actual, real-time use of a RNN-based model as a DT for performing live analysis on an operational CPS. Based on the observed results, we highlight the importance of a DT model's training interval, prediction interval and CPS polling interval in the process of anomaly detection. We uncover the limitations in anomaly detection due to real-time synchronization needs of the RNN-based DT. We highlight this uncovered tug of war between synchronization and anomaly detection is inherent in any complex CPS that is monitored and synchronized by relying on the same sensor streams of ground truth for both synchronization as well as anomaly detection.

Yoginath, Srikanth↗

Volatile Memory Extraction- Based Approach for Level 0-1 CPS Forensics

Most security analyzers operate on system state that is far removed from end-point components in cyber-physical systems (CPS) identified as level 0-1 in the Purdue Architecture Reference Architecture (PERA) [1]. For example, many operate on system logs and other data dumps to disks. Tremendous value that can be gained in cyber security forensics if low level details such as dynamic changes to volatile memory can be extracted and provided to more sophisticated analysis tools. However, obtaining detailed and dynamic system state at the level of volatile memory is extremely challenging [2]. Here, we attempt to apply IT memory forensic mechanisms to CPS end-point devices and statistically evaluate them. Our focus is to extract volatile and dynamically changing internal information form CPS 0-1 level devices, and design preliminary schemes to exploit that extracted information. This new capability of generating a sequence of volatile memory snapshots for offline, detailed and sophisticated analysis opens a new class of cyber security schemes for CPS forensic analysis. As a case study for our ongoing research, we apply the proposed methodology to Modicon PLC using Modbus protocol. We extract the memory layout and subject the device to read operations at the most critical regions of memory. Similarly, write operations are initiated to carefully determine memory locations (for example, bytes that hold the firmware version number). This capability of generating a sequence of volatile memory snapshots for offline, detailed and sophisticated analysis opens a new class of cyber security schemes for CPS forensic analysis. Also, the ability to dynamically make controlled modifications to specific memory locations opens the potential for new mechanisms such as taint analysis and watermarking.

Asmar Awad, Rima↗

Towards Native Execution of Deep Learning on a Leadership-Class HPC System

Large parallel machines generally offer the best parallel performance with "native execution" that is achieved using codes developed with the optimized compilers, communication libraries, and runtimes offered on the machines. In this paper, we report and analyze performance results from native execution of deep learning on a leadership-class high-performance computing (HPC) system. Using our new code called DeepEx, we present a study of the parallel speed up and convergence rates of learning achieved with native parallel execution. In the trade-off between computational parallelism and synchronized convergence, we first focus on maximizing parallelism while still obtaining convergence. Scaling results are reported from execution on up to 15,000 GPUs using two scientific data sets from atom microscopy and protein folding applications, and also using the popular ImageNet data set. In terms of the traditional measure of parallel speed up, excellent scaling is observed up to 12,000 GPUs. Additionally, accounting for convergence rates of deep learning accuracy or error, a deep learning-specific metric called "learning speed up" is also tracked. The performance results indicate the need to evaluate parallel deep learning execution in terms of learning speed up, and point to additional directions for improved exploitation of high-end HPC systems.

Yoginath, Srikanth↗