Saibal Kumar Pal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Saibal Kumar Pal has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Rajan Gupta
Artificial Intelligence & Innovation (AI&I) Lab, Tamaulipas Autonomous University (UAT), Mexico
6 shared publications - Girish Mishra
SAG DRDO Delhi
2 shared publications - Kashif Ahmed
St. Stephen’s College, University of Delhi, Delhi, New Delhi, India
2 shared publications - Maiya Din
DRDO
2 shared publications - R. Mohan
St. Stephen’s College, University of Delhi, Delhi, New Delhi, India
2 shared publications - Somanchi V. S. S. N. V. G. Krishna Murthy
Defence Institute of Advanced Technology
2 shared publications
Latest Publications
- 17 October 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Foundations of Computer Science
- p. 1-29
A Quantum Secure and Efficient RLWE-Based Authenticated Key Exchange Protocol for Mobile Devices
The Ring Learning with Errors (RLWE) problem has emerged as a foundational hardness assumption for post-quantum authenticated key exchange (AKE) protocols. In this paper, we propose a post-quantum and efficient RLWE-Based AKE protocol for mobile devices. We provide formal security reduction in the random oracle model under the decisional RLWE and PRF assumptions. We also show that our scheme is safe against key mismatch attack, signal leakage attack, and provide informal analysis of all standard AKE security properties. Further, we showcase that our scheme also provides perfect forward secrecy and replay attack resistance. Finally, we compare our scheme with several other existing schemes in terms of various security attributes along with computational efficiency to demonstrate its practicality and advantages over the other schemes.
- 17 October 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Foundations of Computer Science
- p. 1-29
A Quantum Secure and Efficient RLWE-Based Authenticated Key Exchange Protocol for Mobile Devices
The Ring Learning with Errors (RLWE) problem has emerged as a foundational hardness assumption for post-quantum authenticated key exchange (AKE) protocols. In this paper, we propose a post-quantum and efficient RLWE-Based AKE protocol for mobile devices. We provide formal security reduction in the random oracle model under the decisional RLWE and PRF assumptions. We also show that our scheme is safe against key mismatch attack, signal leakage attack, and provide informal analysis of all standard AKE security properties. Further, we showcase that our scheme also provides perfect forward secrecy and replay attack resistance. Finally, we compare our scheme with several other existing schemes in terms of various security attributes along with computational efficiency to demonstrate its practicality and advantages over the other schemes.
- 2 January 2026
- Published by Springer Nature
- p. 16-41
Algorithmic Decision-Making in Public Institutions: A Tripartite Analysis of Motivations and Barriers
- 2 January 2026
- Published by Springer Nature
- p. 16-41
Algorithmic Decision-Making in Public Institutions: A Tripartite Analysis of Motivations and Barriers
- Open Access
- 31 October 2025
- Published by Vyom Hans Publications in Vantage: Journal of Thematic Analysis
- Vol. 6 (02) , 93-99
Case Study Analysis on Machine Unlearning Solutions for Large Scale Enterprises
In this paper, we explore how machine unlearning is beginning to change the way large enterprises use AI—particularly in privacy management, compliance, and keeping operations efficient. To provide practical insights, we looked at six major organizations from both global markets and India, spanning fields like banking, e-commerce, healthcare, fintech, and telecom. Their experiences highlight that if privacy-by-design principles are baked into system architecture early, companies can respond much faster to regulatory demands—often cutting wait times by over 95%—and keep the expense of retraining AI models at bay. Our analysis found real benefits in using federated, context-specific, and real-time unlearning solutions, which helped keep model performance above 98% accuracy and bolstered trust with customers and partners. We compared the case studies and a few challenges stood out: dealing with historical data dependencies, plugging new systems into older ones, and building processes that external auditors can trust. These lessons point to the need for teams to actively design for privacy from the start, work jointly across business and technology roles, and put scalable frameworks in place to guide responsible AI development. Ultimately, the study suggests that machine unlearning is quickly becoming an essential part of enterprise AI—especially for those aiming to lead ethically and innovate responsibly. The findings should be valuable to solution architects, business leaders, and regulators involved in building or overseeing modern AI systems.
- 31 October 2025
- Published by Vyom Hans Publications in Vantage: Journal of Thematic Analysis
- Vol. 6 (02) , 93-99
Open AccessCase Study Analysis on Machine Unlearning Solutions for Large Scale Enterprises
In this paper, we explore how machine unlearning is beginning to change the way large enterprises use AI—particularly in privacy management, compliance, and keeping operations efficient. To provide practical insights, we looked at six major organizations from both global markets and India, spanning fields like banking, e-commerce, healthcare, fintech, and telecom. Their experiences highlight that if privacy-by-design principles are baked into system architecture early, companies can respond much faster to regulatory demands—often cutting wait times by over 95%—and keep the expense of retraining AI models at bay. Our analysis found real benefits in using federated, context-specific, and real-time unlearning solutions, which helped keep model performance above 98% accuracy and bolstered trust with customers and partners. We compared the case studies and a few challenges stood out: dealing with historical data dependencies, plugging new systems into older ones, and building processes that external auditors can trust. These lessons point to the need for teams to actively design for privacy from the start, work jointly across business and technology roles, and put scalable frameworks in place to guide responsible AI development. Ultimately, the study suggests that machine unlearning is quickly becoming an essential part of enterprise AI—especially for those aiming to lead ethically and innovate responsibly. The findings should be valuable to solution architects, business leaders, and regulators involved in building or overseeing modern AI systems.
- Top Cited PapersOpen Access
- 12 February 2025
- Published by Association for Computing Machinery (ACM) in Digital Government: Research and Practice
- Vol. 6 (1) , 1-10
Automating Government Report Generation: A Generative AI Approach for Efficient Data Extraction, Analysis, and Visualization
This application paper introduces a transformative solution to address the labour-intensive manual report generation, data searching and report revision process in government entities. Traditional methods of data extraction, analysis, and graph creation for annual reports are not only time-consuming but also prone to human errors. To mitigate these challenges, we propose an innovative system leveraging Generative Artificial Intelligence (GenAI), with a specific focus on large language models (LLMs). Our solution incorporates automated data extraction from diverse sources designated as internal knowledge base, text analysis, summarization using advanced language models, and the generation as well as revisions of informative graphs. Different LLMs like Google's Gemini Pro and OpenAI's GPT 4.0 have been used to read different data visualisation graphs and fetch the information from the internal knowledge base, respectively, to update the graphs in an automated manner. Solution implementation using Python language on the World Economic Situation and Prospects report by the Department of Economic & Social Affairs, United Nation shows that the early result produces almost 0.87% to 17.46% average error rates in the task of factual data visualisation graph. Key benefits of this approach include improved time efficiency, consistency in report format, enhanced insights, and a user-friendly interface. A review and approval workflow facilitate user feedback, contributing to continuous model performance improvement.
- 12 February 2025
- Published by Association for Computing Machinery (ACM) in Digital Government: Research and Practice
- Vol. 6 (1) , 1-10
Top Cited PapersOpen AccessAutomating Government Report Generation: A Generative AI Approach for Efficient Data Extraction, Analysis, and Visualization
This application paper introduces a transformative solution to address the labour-intensive manual report generation, data searching and report revision process in government entities. Traditional methods of data extraction, analysis, and graph creation for annual reports are not only time-consuming but also prone to human errors. To mitigate these challenges, we propose an innovative system leveraging Generative Artificial Intelligence (GenAI), with a specific focus on large language models (LLMs). Our solution incorporates automated data extraction from diverse sources designated as internal knowledge base, text analysis, summarization using advanced language models, and the generation as well as revisions of informative graphs. Different LLMs like Google's Gemini Pro and OpenAI's GPT 4.0 have been used to read different data visualisation graphs and fetch the information from the internal knowledge base, respectively, to update the graphs in an automated manner. Solution implementation using Python language on the World Economic Situation and Prospects report by the Department of Economic & Social Affairs, United Nation shows that the early result produces almost 0.87% to 17.46% average error rates in the task of factual data visualisation graph. Key benefits of this approach include improved time efficiency, consistency in report format, enhanced insights, and a user-friendly interface. A review and approval workflow facilitate user feedback, contributing to continuous model performance improvement.
- Open Access
- 12 March 2024
- Published by Association for Computing Machinery (ACM) in Digital Government: Research and Practice
- Vol. 5 (1) , 1-20
Unsupervised Learning-based Approach for Contextual Understanding of Web Material Around a New Domain of Algorithmic Government
Grasping the contextual nuances is fundamental for efficacious learning in a novel discipline through internet-based research. Such comprehension significantly augments the decision-making process by promoting well-grounded and informed choices. And with advent of machine learning approaches, it becomes even more fast and robust to enable collaboration between machine algorithms and humans. However, human expertise still holds the key for new domain, which has been proposed in this study as a key step in unsupervised learning approach of k -means clustering technique. Domain search term and context terms for the new domain are added to the clustering technique, and the relevance of the resultant groups has been tested. Context setting helps to analyse and understand the content of documents and other sources of information. For a new domain like algorithmic government, which does not have many documents on the web, it was found that contextual learning was up to 40% more relevant than the normal learning approach. The qualitative aspect of the clusters was found much better by the experts than quantitative aspect due to availability of lesser number of search documents. It was found that scientific research also supports the groups formed during contextual learning approach. This approach should help government to better understand and respond to the needs and concerns of their citizens by deriving better data insights in more quickly and to make more informed, evidence-based decisions that are sensitive to the needs and values of different communities and stakeholders. And thus, many stakeholders in the new domain can use this approach for exploration, research, policy formulation, strategizing, implementing, and testing of the various learned concepts. A total of 15 search engines were used in the experimental settings with thousands of web crawling being done using the Carrot 2 engine. Text embedding was done using bag-of-word technique, and k -means clustering was implemented for producing 25 clusters across the two types of learnings.
- 12 March 2024
- Published by Association for Computing Machinery (ACM) in Digital Government: Research and Practice
- Vol. 5 (1) , 1-20
Open AccessUnsupervised Learning-based Approach for Contextual Understanding of Web Material Around a New Domain of Algorithmic Government
Grasping the contextual nuances is fundamental for efficacious learning in a novel discipline through internet-based research. Such comprehension significantly augments the decision-making process by promoting well-grounded and informed choices. And with advent of machine learning approaches, it becomes even more fast and robust to enable collaboration between machine algorithms and humans. However, human expertise still holds the key for new domain, which has been proposed in this study as a key step in unsupervised learning approach of k -means clustering technique. Domain search term and context terms for the new domain are added to the clustering technique, and the relevance of the resultant groups has been tested. Context setting helps to analyse and understand the content of documents and other sources of information. For a new domain like algorithmic government, which does not have many documents on the web, it was found that contextual learning was up to 40% more relevant than the normal learning approach. The qualitative aspect of the clusters was found much better by the experts than quantitative aspect due to availability of lesser number of search documents. It was found that scientific research also supports the groups formed during contextual learning approach. This approach should help government to better understand and respond to the needs and concerns of their citizens by deriving better data insights in more quickly and to make more informed, evidence-based decisions that are sensitive to the needs and values of different communities and stakeholders. And thus, many stakeholders in the new domain can use this approach for exploration, research, policy formulation, strategizing, implementing, and testing of the various learned concepts. A total of 15 search engines were used in the experimental settings with thousands of web crawling being done using the Carrot 2 engine. Text embedding was done using bag-of-word technique, and k -means clustering was implemented for producing 25 clusters across the two types of learnings.
- 16 September 2023
- Published by Springer Nature
- p. 185-203
Improving E-Governance Through Application of Hyperautomation
- 16 September 2023
- Published by Springer Nature
- p. 185-203
Improving E-Governance Through Application of Hyperautomation
- 5 May 2023
- Published by Springer Nature in Journal of Earth System Science
- Vol. 132 (2) , 1-17
Delineation of thin and discrete sand reservoir facies from shale-dominated Kopili Formation (Middle to Late Eocene) using the post-stack seismic inversion and neural network algorithm: A case study from Assam Basin, India
- 5 May 2023
- Published by Springer Nature in Journal of Earth System Science
- Vol. 132 (2) , 1-17
Delineation of thin and discrete sand reservoir facies from shale-dominated Kopili Formation (Middle to Late Eocene) using the post-stack seismic inversion and neural network algorithm: A case study from Assam Basin, India
- 10 February 2023
- Published by Taylor & Francis in Cryptologia
- Vol. 48 (2) , 173-192
Bit inclusion test: an enhanced avalanche test for stream ciphers
In this paper, we present a new test for stream ciphers named the ‘Bit Inclusion Test (BIT)’. This test provides an enhancement to the conventional avalanche test for stream ciphers. This test is efficient and includes the conventional avalanche test. Additionally, it can capture the shortcomings which escape the conventional avalanche test. We also demonstrate, with examples, how BIT is capable of going deeper into the structure of crypto-algorithms and detecting internal biases which make an algorithm susceptible to cryptanalytic attacks.
- 10 February 2023
- Published by Taylor & Francis in Cryptologia
- Vol. 48 (2) , 173-192
Bit inclusion test: an enhanced avalanche test for stream ciphers
In this paper, we present a new test for stream ciphers named the ‘Bit Inclusion Test (BIT)’. This test provides an enhancement to the conventional avalanche test for stream ciphers. This test is efficient and includes the conventional avalanche test. Additionally, it can capture the shortcomings which escape the conventional avalanche test. We also demonstrate, with examples, how BIT is capable of going deeper into the structure of crypto-algorithms and detecting internal biases which make an algorithm susceptible to cryptanalytic attacks.
- 14 July 2022
- Published by Taylor & Francis in Communications in Algebra
- Vol. 51 (1) , 214-223
Key exchange protocol based upon a modified tropical structure
In this article, we make use of an algebraic structure that is derived from a tropical semiring and present a key exchange scheme based on it. This is followed by a security analysis of the protocol. We conclude the article by showing that this scheme is more secure than its other tropical counterparts.
- 14 July 2022
- Published by Taylor & Francis in Communications in Algebra
- Vol. 51 (1) , 214-223
Key exchange protocol based upon a modified tropical structure
In this article, we make use of an algebraic structure that is derived from a tropical semiring and present a key exchange scheme based on it. This is followed by a security analysis of the protocol. We conclude the article by showing that this scheme is more secure than its other tropical counterparts.
- 2 January 2022
- Published by Taylor & Francis in Cryptologia
- Vol. 47 (1) , 63-87
A review of the tropical approach in cryptography
In this article, we survey and analyze the role of tropical semirings in key-exchange protocols proposed in the past decade. We also present new ideas on cryptanalysis of some tropical key agreement techniques suggested during this period.
- 2 January 2022
- Published by Taylor & Francis in Cryptologia
- Vol. 47 (1) , 63-87
A review of the tropical approach in cryptography
In this article, we survey and analyze the role of tropical semirings in key-exchange protocols proposed in the past decade. We also present new ideas on cryptanalysis of some tropical key agreement techniques suggested during this period.