Lavanya Elluri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lavanya Elluri has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Deepti Gupta
Subhani Department of Computer Information Systems, Texas A&M University-Central Texas, Killeen, TX 76549, USA
3 shared publications - Karuna Pande Joshi
University of Maryland Baltimore County
3 shared publications - Varun Mandalapu
Information Systems University of Maryland Baltimore County 1000 Hilltop Cir 21250 Baltimore MD USA
3 shared publications Anantaa Kotal
2 shared publicationsAnupam Joshi
Department of Computer Science, University of Maryland at Baltimore County (UMBC), Baltimore, MD, USA
2 shared publications- Rahul Dwivedi
Subhani Department of Computer Information Systems, Texas A&M University - Central Texas, Killeen, USA
2 shared publications
Latest Publications
- Open Access
- 8 October 2026
- Published by Elsevier in SSRN Electronic Journal
Agentic Knowledge Graph Management for IoT Manufacturer Privacy Policy Assessment
Assessing Internet of Things (IoT) manufacturers' privacy policies requires both structured representations of cybersecurity requirements and a current collection of policy documents. Existing approaches to knowledge graph (KG) construction and policy analysis provide foundations for this task, but maintaining policy content as manufacturers revise their disclosures remains a distinct challenge. We present an agentic framework that discovers, retrieves, and maintains manufacturer privacy policies in an ontology-based KG. Building on a repository of 802 manufacturers, the framework combines a discovery agent directed by a large language model with controlled update operations, policy version history, and maintenance timestamps. It supports on-demand checks and is configured for quarterly maintenance. The maintained policies feed a web-based assessment tool that combines rule-based evidence, graph queries, and semantic similarity to identify textual coverage of concepts drawn from California SB-327, Oregon HB-2395, NISTIR 8259, and Public Law 116-207. Compared with an adapted AutoKG baseline, the proposed framework achieved policy URL accuracy of 0.92 versus 0.85 and change-detection accuracy of 0.91 versus 0.84. These descriptive results support further evaluation of agentic policy maintenance. Ultimately, this framework assesses policy statements against regulatory statutes; it does not represent the determinant in legal compliance for IoT manufacturers.
- 8 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAgentic Knowledge Graph Management for IoT Manufacturer Privacy Policy Assessment
Assessing Internet of Things (IoT) manufacturers' privacy policies requires both structured representations of cybersecurity requirements and a current collection of policy documents. Existing approaches to knowledge graph (KG) construction and policy analysis provide foundations for this task, but maintaining policy content as manufacturers revise their disclosures remains a distinct challenge. We present an agentic framework that discovers, retrieves, and maintains manufacturer privacy policies in an ontology-based KG. Building on a repository of 802 manufacturers, the framework combines a discovery agent directed by a large language model with controlled update operations, policy version history, and maintenance timestamps. It supports on-demand checks and is configured for quarterly maintenance. The maintained policies feed a web-based assessment tool that combines rule-based evidence, graph queries, and semantic similarity to identify textual coverage of concepts drawn from California SB-327, Oregon HB-2395, NISTIR 8259, and Public Law 116-207. Compared with an adapted AutoKG baseline, the proposed framework achieved policy URL accuracy of 0.92 versus 0.85 and change-detection accuracy of 0.91 versus 0.84. These descriptive results support further evaluation of agentic policy maintenance. Ultimately, this framework assesses policy statements against regulatory statutes; it does not represent the determinant in legal compliance for IoT manufacturers.
- Open Access
- 20 February 2026
- Published by Springer Nature in International Journal of Information Security
- Vol. 25 (2) , 59
Exploring IoT privacy compliance research: a topic modeling approach
- 20 February 2026
- Published by Springer Nature in International Journal of Information Security
- Vol. 25 (2) , 59
Open AccessExploring IoT privacy compliance research: a topic modeling approach
- Open Access
Modeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integration
The development of robust transliteration techniques to enhance the effectiveness of transforming Romanized scripts into native scripts is crucial for Natural Language Processing tasks, including sentiment analysis, speech recognition, information retrieval, and intelligent personal assistants. Despite significant advancements, state-of-the-art multilingual models still face challenges in handling Romanized script, where the Roman alphabet is adopted to represent the phonetic structure of diverse languages. Within the South Asian context, where the use of Romanized script for Indo-Aryan languages is widespread across social media and digital communication platforms, such usage continues to pose significant challenges for cutting-edge multilingual models. While a limited number of transliteration datasets and models are available for Indo-Aryan languages, they generally lack sufficient diversity in pronunciation and spelling variations, adequate code-mixed data for large language model (LLM) training, and low-resource adaptation. To address this research gap, we introduce a novel transliteration dataset for two popular Indo-Aryan languages, Hindi and Bengali, which are ranked as the 3rd and 7th most spoken languages worldwide. Our dataset comprises nearly 1.8 million Hindi and 1 million Bengali transliteration pairs. In addition to that, we pre-train a custom multilingual seq2seq LLM based on Marian architecture using the developed dataset. Experimental results demonstrate significant improvements compared to existing relevant models in terms of BLEU and CER metrics.
Open AccessModeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integration
The development of robust transliteration techniques to enhance the effectiveness of transforming Romanized scripts into native scripts is crucial for Natural Language Processing tasks, including sentiment analysis, speech recognition, information retrieval, and intelligent personal assistants. Despite significant advancements, state-of-the-art multilingual models still face challenges in handling Romanized script, where the Roman alphabet is adopted to represent the phonetic structure of diverse languages. Within the South Asian context, where the use of Romanized script for Indo-Aryan languages is widespread across social media and digital communication platforms, such usage continues to pose significant challenges for cutting-edge multilingual models. While a limited number of transliteration datasets and models are available for Indo-Aryan languages, they generally lack sufficient diversity in pronunciation and spelling variations, adequate code-mixed data for large language model (LLM) training, and low-resource adaptation. To address this research gap, we introduce a novel transliteration dataset for two popular Indo-Aryan languages, Hindi and Bengali, which are ranked as the 3rd and 7th most spoken languages worldwide. Our dataset comprises nearly 1.8 million Hindi and 1 million Bengali transliteration pairs. In addition to that, we pre-train a custom multilingual seq2seq LLM based on Marian architecture using the developed dataset. Experimental results demonstrate significant improvements compared to existing relevant models in terms of BLEU and CER metrics.
- 22 October 2025
- Published by Elsevier in Computers & Security
- Vol. 161
Scalable automation for IoT cyberSecurity compliance: Ontology-driven reasoning for real-time assessment
- 22 October 2025
- Published by Elsevier in Computers & Security
- Vol. 161
Scalable automation for IoT cyberSecurity compliance: Ontology-driven reasoning for real-time assessment
- Open Access
PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction
Redacting Personally Identifiable Information (PII) from unstructured text is critical for ensuring data privacy in regulated domains. While earlier approaches have relied on rule-based systems and domain-specific Named Entity Recognition (NER) models, these methods fail to generalize across formats and contexts. Recent advances in Large Language Models (LLMs) offer a promising alternative, yet the effect of architectural and training choices on redaction performance remains underexplored. LLMs have demonstrated strong performance in tasks that require contextual language understanding, including the redaction of PII in free-form text. Prior work suggests that with appropriate adaptation, LLMs can become effective contextual privacy learners. However, the consequences of architectural and training choices for PII Redaction remain underexplored. In this work, we present a comprehensive analysis of LLMs as privacy-preserving PII Redaction systems. We evaluate a range of LLM architectures and training strategies for their effectiveness in PII Redaction. Our analysis measures redaction performance, semantic preservation, and PII leakage, and compares these outcomes against latency and computational cost. The results provide practical guidance for configuring LLM-based redactors that are accurate, efficient, and privacy-aware. To support reproducibility and real-world deployment, we release PRvL, an open-source suite of fine-tuned models, and evaluation tools for general-purpose PII Redaction. PRvL is built entirely on open-source LLMs and supports multiple inference settings for flexibility and compliance. It is designed to be easily customized for different domains and fully operable within secure, self-managed environments. This enables data owners to perform redactions without relying on third-party services or exposing sensitive content beyond their own infrastructure.
Open AccessPRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction
Redacting Personally Identifiable Information (PII) from unstructured text is critical for ensuring data privacy in regulated domains. While earlier approaches have relied on rule-based systems and domain-specific Named Entity Recognition (NER) models, these methods fail to generalize across formats and contexts. Recent advances in Large Language Models (LLMs) offer a promising alternative, yet the effect of architectural and training choices on redaction performance remains underexplored. LLMs have demonstrated strong performance in tasks that require contextual language understanding, including the redaction of PII in free-form text. Prior work suggests that with appropriate adaptation, LLMs can become effective contextual privacy learners. However, the consequences of architectural and training choices for PII Redaction remain underexplored. In this work, we present a comprehensive analysis of LLMs as privacy-preserving PII Redaction systems. We evaluate a range of LLM architectures and training strategies for their effectiveness in PII Redaction. Our analysis measures redaction performance, semantic preservation, and PII leakage, and compares these outcomes against latency and computational cost. The results provide practical guidance for configuring LLM-based redactors that are accurate, efficient, and privacy-aware. To support reproducibility and real-world deployment, we release PRvL, an open-source suite of fine-tuned models, and evaluation tools for general-purpose PII Redaction. PRvL is built entirely on open-source LLMs and supports multiple inference settings for flexibility and compliance. It is designed to be easily customized for different domains and fully operable within secure, self-managed environments. This enables data owners to perform redactions without relying on third-party services or exposing sensitive content beyond their own infrastructure.
- Open Access
Blockchain-Enhanced Framework for Secure Third-Party Vendor Risk Management and Vigilant Security Controls
In an era of heightened digital interconnectedness, businesses increasingly rely on third-party vendors to enhance their operational capabilities. However, this growing dependency introduces significant security risks, making it crucial to develop a robust framework to mitigate potential vulnerabilities. This paper proposes a comprehensive secure framework for managing third-party vendor risk, integrating blockchain technology to ensure transparency, traceability, and immutability in vendor assessments and interactions. By leveraging blockchain, the framework enhances the integrity of vendor security audits, ensuring that vendor assessments remain up-to-date and tamperproof. This proposed framework leverages smart contracts to reduce human error while ensuring real-time monitoring of compliance and security controls. By evaluating critical security controls-such as data encryption, access control mechanisms, multi-factor authentication, and zero-trust architecture-this approach strengthens an organization's defense against emerging cyber threats. Additionally, continuous monitoring enabled by blockchain ensures the immutability and transparency of vendor compliance processes. In this paper, a case study on iHealth's transition to AWS Cloud demonstrates the practical implementation of the framework, showing a significant reduction in vulnerabilities and marked improvement in incident response times. Through the adoption of this blockchain-enabled approach, organizations can mitigate vendor risks, streamline compliance, and enhance their overall security posture.
Open AccessBlockchain-Enhanced Framework for Secure Third-Party Vendor Risk Management and Vigilant Security Controls
In an era of heightened digital interconnectedness, businesses increasingly rely on third-party vendors to enhance their operational capabilities. However, this growing dependency introduces significant security risks, making it crucial to develop a robust framework to mitigate potential vulnerabilities. This paper proposes a comprehensive secure framework for managing third-party vendor risk, integrating blockchain technology to ensure transparency, traceability, and immutability in vendor assessments and interactions. By leveraging blockchain, the framework enhances the integrity of vendor security audits, ensuring that vendor assessments remain up-to-date and tamperproof. This proposed framework leverages smart contracts to reduce human error while ensuring real-time monitoring of compliance and security controls. By evaluating critical security controls-such as data encryption, access control mechanisms, multi-factor authentication, and zero-trust architecture-this approach strengthens an organization's defense against emerging cyber threats. Additionally, continuous monitoring enabled by blockchain ensures the immutability and transparency of vendor compliance processes. In this paper, a case study on iHealth's transition to AWS Cloud demonstrates the practical implementation of the framework, showing a significant reduction in vulnerabilities and marked improvement in incident response times. Through the adoption of this blockchain-enabled approach, organizations can mitigate vendor risks, streamline compliance, and enhance their overall security posture.
- Open Access
- 27 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 119884-119902
Exploring Generative Artificial Intelligence Research: A Bibliometric Analysis Approach
Artificial Intelligence (AI) and its many applications are changing our lives in ways we could not have imagined a decade ago. Generative artificial intelligence is an artificial intelligence system capable of generating texts, images, and other media based on the input training data. Although still in their early stages, numerous examples of such systems in different domains have gained widespread attention from the public, media, policymakers, and researchers. This study aims to explore the generative AI academic research in the past decade using bibliometrics text analysis, and social network analysis. Specifically, research themes and their relationships, the evolution of research themes over time, and prominent authors, articles, journals, institutions, and countries publishing in generative AI are identified. The data was further found to partially support the classical bibliometrics laws of Zipf, and Bradford’s. The two overarching research themes identified using knowledge synthesis from most cited articles and journals are technical advancements and developments in generative AI systems; and their applications to image processing, pattern recognition, and computer vision. ChatGPT, large language models, and the application of generative AI to healthcare and education are emerging research topics. In addition to the applications of generative AI to healthcare and education, its usefulness to geoscience, remote sensing, Internet of Things(IoT), and cybersecurity are discussed.
- 27 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 119884-119902
Open AccessExploring Generative Artificial Intelligence Research: A Bibliometric Analysis Approach
Artificial Intelligence (AI) and its many applications are changing our lives in ways we could not have imagined a decade ago. Generative artificial intelligence is an artificial intelligence system capable of generating texts, images, and other media based on the input training data. Although still in their early stages, numerous examples of such systems in different domains have gained widespread attention from the public, media, policymakers, and researchers. This study aims to explore the generative AI academic research in the past decade using bibliometrics text analysis, and social network analysis. Specifically, research themes and their relationships, the evolution of research themes over time, and prominent authors, articles, journals, institutions, and countries publishing in generative AI are identified. The data was further found to partially support the classical bibliometrics laws of Zipf, and Bradford’s. The two overarching research themes identified using knowledge synthesis from most cited articles and journals are technical advancements and developments in generative AI systems; and their applications to image processing, pattern recognition, and computer vision. ChatGPT, large language models, and the application of generative AI to healthcare and education are emerging research topics. In addition to the applications of generative AI to healthcare and education, its usefulness to geoscience, remote sensing, Internet of Things(IoT), and cybersecurity are discussed.
- 30 June 2024
- Published by Springer Nature
- p. 15-26
Secure and Privacy-Compliant Data Sharing: An Essential Framework for Healthcare Organizations
- 30 June 2024
- Published by Springer Nature
- p. 15-26
Secure and Privacy-Compliant Data Sharing: An Essential Framework for Healthcare Organizations
- Open Access
Privacy-Preserving Data Sharing in Agriculture: Enforcing Policy Rules for Secure and Confidential Data Synthesis
Big Data empowers the farming community with the information needed to optimize resource usage, increase productivity, and enhance the sustainability of agricultural practices. The use of Big Data in farming requires the collection and analysis of data from various sources such as sensors, satellites, and farmer surveys. While Big Data can provide the farming community with valuable insights and improve efficiency, there is significant concern regarding the security of this data as well as the privacy of the participants. Privacy regulations, such as the EU GDPR, the EU Code of Conduct on agricultural data sharing by contractual agreement, and the proposed EU AI law, have been created to address the issue of data privacy and provide specific guidelines on when and how data can be shared between organizations. To make confidential agricultural data widely available for Big Data analysis without violating the privacy of the data subjects, we consider privacy-preserving methods of data sharing in agriculture. Deep learning-based synthetic data generation has been proposed for privacy-preserving data sharing. However, there is a lack of compliance with documented data privacy policies in such privacy-preserving efforts. In this study, we propose a novel framework for enforcing privacy policy rules in privacy-preserving data generation algorithms. We explore several available agricultural codes of conduct, extract knowledge related to the privacy constraints in data, and use the extracted knowledge to define privacy bounds in a privacy-preserving generative model. We use our framework to generate synthetic agricultural data and present experimental results that demonstrate the utility of the synthetic dataset in downstream tasks. We also show that our framework can evade potential threats and secure data based on applicable regulatory policy rules.
Open AccessPrivacy-Preserving Data Sharing in Agriculture: Enforcing Policy Rules for Secure and Confidential Data Synthesis
Big Data empowers the farming community with the information needed to optimize resource usage, increase productivity, and enhance the sustainability of agricultural practices. The use of Big Data in farming requires the collection and analysis of data from various sources such as sensors, satellites, and farmer surveys. While Big Data can provide the farming community with valuable insights and improve efficiency, there is significant concern regarding the security of this data as well as the privacy of the participants. Privacy regulations, such as the EU GDPR, the EU Code of Conduct on agricultural data sharing by contractual agreement, and the proposed EU AI law, have been created to address the issue of data privacy and provide specific guidelines on when and how data can be shared between organizations. To make confidential agricultural data widely available for Big Data analysis without violating the privacy of the data subjects, we consider privacy-preserving methods of data sharing in agriculture. Deep learning-based synthetic data generation has been proposed for privacy-preserving data sharing. However, there is a lack of compliance with documented data privacy policies in such privacy-preserving efforts. In this study, we propose a novel framework for enforcing privacy policy rules in privacy-preserving data generation algorithms. We explore several available agricultural codes of conduct, extract knowledge related to the privacy constraints in data, and use the extracted knowledge to define privacy bounds in a privacy-preserving generative model. We use our framework to generate synthetic agricultural data and present experimental results that demonstrate the utility of the synthetic dataset in downstream tasks. We also show that our framework can evade potential threats and secure data based on applicable regulatory policy rules.
- Top Cited PapersOpen Access
- 14 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 60153-60170
Crime Prediction Using Machine Learning and Deep Learning: A Systematic Review and Future Directions
Predicting crime using machine learning and deep learning techniques has gained considerable attention from researchers in recent years, focusing on identifying patterns and trends in crime occurrences. This review paper examines over 150 articles to explore the various machine learning and deep learning algorithms applied to predict crime. The study provides access to the datasets used for crime prediction by researchers and analyzes prominent approaches applied in machine learning and deep learning algorithms to predict crime, offering insights into different trends and factors related to criminal activities. Additionally, the paper highlights potential gaps and future directions that can enhance the accuracy of crime prediction. Finally, the comprehensive overview of research discussed in this paper on crime prediction using machine learning and deep learning approaches serves as a valuable reference for researchers in this field. By gaining a deeper understanding of crime prediction techniques, law enforcement agencies can develop strategies to prevent and respond to criminal activities more effectively.
- 14 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 60153-60170
Top Cited PapersOpen AccessCrime Prediction Using Machine Learning and Deep Learning: A Systematic Review and Future Directions
Predicting crime using machine learning and deep learning techniques has gained considerable attention from researchers in recent years, focusing on identifying patterns and trends in crime occurrences. This review paper examines over 150 articles to explore the various machine learning and deep learning algorithms applied to predict crime. The study provides access to the datasets used for crime prediction by researchers and analyzes prominent approaches applied in machine learning and deep learning algorithms to predict crime, offering insights into different trends and factors related to criminal activities. Additionally, the paper highlights potential gaps and future directions that can enhance the accuracy of crime prediction. Finally, the comprehensive overview of research discussed in this paper on crime prediction using machine learning and deep learning approaches serves as a valuable reference for researchers in this field. By gaining a deeper understanding of crime prediction techniques, law enforcement agencies can develop strategies to prevent and respond to criminal activities more effectively.