Browsing by Author "Thukkaraju, Ashrith Reddy"

Now showing 1 - 2 of 2
  • Thumbnail Image
    CS5604: Team 1 ETD Collection Management
    Jain, Tanya; Bhagat, Hirva; Lee, Wen-Yu; Thukkaraju, Ashrith Reddy; Sethi, Raghav (Virginia Tech, 2023-01-13)
    Academic institutions the world over are known to produce hundreds of thousands of ETDs (Electronic Theses and Dissertations) every year. At the end of an academic year, we are left with large volumes of ETD data that are rarely used for further research or ever cited in future work, writings, or publications. As part of the CS5604: Information Storage and Retrieval graduate-level course at Virginia Polytechnic Institute and State University (Virginia Tech), we collectively created a search engine for a collection of more than 500,000 ETDs from academic institutions in the United States, which constitutes the class-wide project. This system enables users to ingest, pre-process, and store ETDs in a repository; apply deep learning models to perform topic modeling, text segmentation, chapter summarization, and classification, backed by a DevOps, user experience and integrations team. We are Team 1 or the “ETD Collection Management” team. During the course of the Fall 2022 semester at Virginia Tech, we were responsible for setting up the repository of ETDs, which encompasses broadly the following three components: (1) setting up a database, (2) storing digital objects in a file system, and (3) creating a knowledge graph. Our work enabled other teams to efficiently retrieve the stored ETD data, and perform appropriate pre-processing operations, and during the final few months of the semester, to apply the aforementioned deep learning models to the ETD collection we created. The key deliverable for Team 1 was to create an interactive user interface to perform CRUD operations (create, retrieve, update, and delete) in order to interact with the repository of ETDs, which is essentially an extrapolation of the work already taken up at Virginia Tech’s Digital Library Research Laboratory. Owing to the fact that the other teams had no direct access to the repository set up by us, we designed a host of Application Programming Interfaces (APIs) which are elaborated in depth in the subsequent sections of the report. The end goal for Team 1 was to be able to set up an accessible repository of ETDs so that they can be used for further research work. This is taking into account how each ETD is a well-curated resource and how it may even prove to be an excellent asset for an in-depth analysis on a certain topic, not limited to academic or research purposes.
  • Thumbnail Image
    Interdependent Mission Impact Assessment of an IoT System with Hypergame-Theoretic Attack-Defense Behavior Modeling
    Thukkaraju, Ashrith Reddy (Virginia Tech, 2023-11-17)
    Mission impact assessment (MIA) research has been explored to evaluate the performance and effectiveness of a mission system, such as enterprise networks with organizational missions and military or tactical mission teams with assigned missions. The key components in such mission systems, including assets, services, tasks, vulnerability, attacks, and defenses, are interdependent, and their impacts are interwoven. However, the current state-of-the-art MIA approaches have less studied such interdependencies. In addition, they have not modeled strategic attack-defense interactions under partial observability. In this work, we propose a novel MIA framework that assesses measures of performance (MoP) or measures of effectiveness (MoE) based on the service requirements (e.g., correctness or timeliness) of a given mission system based on full and comprehensive modeling and simulation of the key system components and their interdependencies. Particularly, we model intelligent attack-defense strategy selections based on hypergame theory, which allows considering uncertainty in estimating each player's hypergame expected utility (HEU) for its best strategy selection. As the case study, we consider an Internet-of-Things (IoT)-based mission system aiming to accurately and timely detect an object, given stringent accuracy and time constraints for successful mission completion. Via extensive simulation experiments, we validate the quality of the proposed MIA tool in its inference accuracy of the mission performance under a wide range of different environmental settings hindering the mission performance assessment and attack-defense interactions. Our results prove that the developed MIA framework shows a sufficiently high inference accuracy (e.g., 80%) even with a small portion of the training dataset (e.g., 20-50%). We also found the MIA can better assess the system's mission performance when attackers exhibit clearer patterns to take more strategic actions using hypergame theory.