S. Sitharama Iyengar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
S. Sitharama Iyengar has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Abdur Rahman Shahid
School of Computing Southern Illinois University Carbondale IL USA
2 shared publications K R Venugopal
Bangalore University,Bengaluru,India
2 shared publicationsL M Patnaik
INSA, National Institute of Advanced Studies,Indian Institute of Science Campus,Bangalore,India
2 shared publications- Niki Pissinou
Florida International University, Miami, FL, USA
2 shared publications - Amith Kamath Belman
San Jose State University, USA
1 shared publication C M Geeta
University Visvesvaraya College of Engineering, Bangalore, India
1 shared publication
Latest Publications
- Open Access
- 16 March 2026
- Published by Association for Computing Machinery (ACM) in Digital Threats: Research and Practice
- Vol. 7 (1) , 1-15
Enhancing Digital Security: A Novel Dual-Paradigm Approach for Robust Deepfake Detection Using Pre and Post Quantum-Trained Neural Networks
The rapid rise of deepfake technology continues to challenge digital security, trust, and misinformation control particularly for celebrities and public figures, whose identities are frequently exploited. This article introduces a novel dual paradigm deepfake detection framework that integrates a classical attention-enhanced EfficientNetB4 model with a Quantum Trained Convolutional Neural Network (QT-CNN). The classical stage leverages spatial attention and siamese feature alignment to highlight manipulation sensitive facial regions and improve cross-dataset generalization. Building on this, the QT-CNN employs parameterized quantum circuits and quantum-to-classical parameter mapping to reduce model complexity while preserving detection accuracy. Comprehensive experiments on a large-scale South Asian celebrity dataset, an underrepresented demographic in existing benchmarks alongside FF++ and DFDC, demonstrate that the hybrid approach achieves robust performance, including 94.5% accuracy on in-distribution data and strong generalization under demographic, corruption, and compression shifts. The QT-CNN further reduces trainable parameters by nearly 70%, suggesting a promising pathway for efficient deployment in resource-constrained, high-volume environments such as social media moderation pipelines. This work contributes a scalable, demographically inclusive, and quantum informed methodology toward securing digital ecosystems in both current and emerging post quantum environments.
- 16 March 2026
- Published by Association for Computing Machinery (ACM) in Digital Threats: Research and Practice
- Vol. 7 (1) , 1-15
Open AccessEnhancing Digital Security: A Novel Dual-Paradigm Approach for Robust Deepfake Detection Using Pre and Post Quantum-Trained Neural Networks
The rapid rise of deepfake technology continues to challenge digital security, trust, and misinformation control particularly for celebrities and public figures, whose identities are frequently exploited. This article introduces a novel dual paradigm deepfake detection framework that integrates a classical attention-enhanced EfficientNetB4 model with a Quantum Trained Convolutional Neural Network (QT-CNN). The classical stage leverages spatial attention and siamese feature alignment to highlight manipulation sensitive facial regions and improve cross-dataset generalization. Building on this, the QT-CNN employs parameterized quantum circuits and quantum-to-classical parameter mapping to reduce model complexity while preserving detection accuracy. Comprehensive experiments on a large-scale South Asian celebrity dataset, an underrepresented demographic in existing benchmarks alongside FF++ and DFDC, demonstrate that the hybrid approach achieves robust performance, including 94.5% accuracy on in-distribution data and strong generalization under demographic, corruption, and compression shifts. The QT-CNN further reduces trainable parameters by nearly 70%, suggesting a promising pathway for efficient deployment in resource-constrained, high-volume environments such as social media moderation pipelines. This work contributes a scalable, demographically inclusive, and quantum informed methodology toward securing digital ecosystems in both current and emerging post quantum environments.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 12605-12627
Machine Learning-Enhanced Malware Obfuscation and Innovative Defense Strategies
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 12605-12627
Open AccessMachine Learning-Enhanced Malware Obfuscation and Innovative Defense Strategies
- Open Access
- 20 April 2021
- Published by Association for Computing Machinery (ACM) in Digital Threats: Research and Practice
- Vol. 2 (2) , 1-24
Game Theory based Cyber-Insurance to Cover Potential Loss from Mobile Malware Exploitation
Potential for huge loss from malicious exploitation of software calls for development of principles of cyber-insurance. Estimating what to insure and for how much and what might be the premiums poses challenges because of the uncertainties, such as the timings of emergence and lethality of malicious apps, human propensity to favor ease by giving more privilege to downloaded apps over inconvenience of delay or functionality, the chance of infection determined by the lifestyle of the mobile device user, and the monetary value of the compromise of software, and so on. We provide a theoretical framework for cyber-insurance backed by game-theoretic formulation to calculate monetary value of risk and the insurance premiums associated with software compromise. By establishing the conditions for Nash equilibrium between strategies of an adversary and software we derive probabilities for risk, potential loss, gain to adversary from app categories, such as lifestyles, entertainment, education, and so on, and their prevalence ratios. Using simulations over a range of possibilities, and using publicly available malware statistics, we provide insights about the strategies that can be taken by the software and the adversary. We show the application of our framework on the most recent mobile malware data (2018 ISTR report—data for the year 2017) that consists of the top five Android malware apps: Malapp, Fakeinst, Premiumtext, Maldownloader , and Simplelocker and the resulting leaked phone number, location information, and installed app information. Uniqueness of our work stems from developing mathematical framework and providing insights of estimating cyber-insurance parameters through game-theoretic choice of strategies and by showing its efficacy on a recent real malicious app data . These insights will be of tremendous help to researchers and practitioners in the security community.
- 20 April 2021
- Published by Association for Computing Machinery (ACM) in Digital Threats: Research and Practice
- Vol. 2 (2) , 1-24
Open AccessGame Theory based Cyber-Insurance to Cover Potential Loss from Mobile Malware Exploitation
Potential for huge loss from malicious exploitation of software calls for development of principles of cyber-insurance. Estimating what to insure and for how much and what might be the premiums poses challenges because of the uncertainties, such as the timings of emergence and lethality of malicious apps, human propensity to favor ease by giving more privilege to downloaded apps over inconvenience of delay or functionality, the chance of infection determined by the lifestyle of the mobile device user, and the monetary value of the compromise of software, and so on. We provide a theoretical framework for cyber-insurance backed by game-theoretic formulation to calculate monetary value of risk and the insurance premiums associated with software compromise. By establishing the conditions for Nash equilibrium between strategies of an adversary and software we derive probabilities for risk, potential loss, gain to adversary from app categories, such as lifestyles, entertainment, education, and so on, and their prevalence ratios. Using simulations over a range of possibilities, and using publicly available malware statistics, we provide insights about the strategies that can be taken by the software and the adversary. We show the application of our framework on the most recent mobile malware data (2018 ISTR report—data for the year 2017) that consists of the top five Android malware apps: Malapp, Fakeinst, Premiumtext, Maldownloader , and Simplelocker and the resulting leaked phone number, location information, and installed app information. Uniqueness of our work stems from developing mathematical framework and providing insights of estimating cyber-insurance parameters through game-theoretic choice of strategies and by showing its efficacy on a recent real malicious app data . These insights will be of tremendous help to researchers and practitioners in the security community.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Automatic Classification of Community Question Answer (CQA) for Non Factoid Queries
Owing to the steep increase in the Internet population, the content over the web is increasing exponentially so as Community Question Answer (CQA) have acquired very huge amount of questions and answers. In this article, a machine learning algorithms are utilized for Question Classification (QC) and Answer Classification (AC). We identify the category of the question posted and further map with the corresponding question. Similarly for the answers posted by the multiple user will be processed for category mapping. Here the result shows the effective classifier that can be chosen to perform the mapping task for both Question classifier as well as answer classifier. Here the results shows that, for Question Classification (QA), Linear Support Vector Classification (LSVC) is found to be best classifier and Multinomial Logistic Regression (MLR) is most suitable for Answer Classification (AC). Using the probability of overall possible outcomes of a particular answer will give a best answer. Experiments results shows that our method outperforms efficiently.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Automatic Classification of Community Question Answer (CQA) for Non Factoid Queries
Owing to the steep increase in the Internet population, the content over the web is increasing exponentially so as Community Question Answer (CQA) have acquired very huge amount of questions and answers. In this article, a machine learning algorithms are utilized for Question Classification (QC) and Answer Classification (AC). We identify the category of the question posted and further map with the corresponding question. Similarly for the answers posted by the multiple user will be processed for category mapping. Here the result shows the effective classifier that can be chosen to perform the mapping task for both Question classifier as well as answer classifier. Here the results shows that, for Question Classification (QA), Linear Support Vector Classification (LSVC) is found to be best classifier and Multinomial Logistic Regression (MLR) is most suitable for Answer Classification (AC). Using the probability of overall possible outcomes of a particular answer will give a best answer. Experiments results shows that our method outperforms efficiently.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 17-18
KLAP for Real-World Protection of Location Privacy
In Location-Based Services (LBS), users are required to disclose their precise location information to query a service provider. An untrusted service provider can abuse those queries to infer sensitive information on a user through spatio-temporal and historical data analyses. Depicting the drawbacks of existing privacy-preserving approaches in LBS, we propose a user-centric obfuscation approach, called KLAP, based on the three fundamental obfuscation requirements: k number of locations, l-diversity, and privacy area preservation. Considering user's sensitivity to different locations and utilizing Real-Time Traffic Information (RTTI), KLAP generates a convex Concealing Region (CR) to hide user's location such that the locations, forming the CR, resemble similar sensitivity and are resilient against a wide range of inferences in spatio-temporal domain. For the first time, a novel CR pruning technique is proposed to significantly improve the delay between successive CR submissions. We carry out an experiment with a real dataset to show its effectiveness for sporadic, frequent, and continuous service use cases.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 17-18
KLAP for Real-World Protection of Location Privacy
In Location-Based Services (LBS), users are required to disclose their precise location information to query a service provider. An untrusted service provider can abuse those queries to infer sensitive information on a user through spatio-temporal and historical data analyses. Depicting the drawbacks of existing privacy-preserving approaches in LBS, we propose a user-centric obfuscation approach, called KLAP, based on the three fundamental obfuscation requirements: k number of locations, l-diversity, and privacy area preservation. Considering user's sensitivity to different locations and utilizing Real-Time Traffic Information (RTTI), KLAP generates a convex Concealing Region (CR) to hide user's location such that the locations, forming the CR, resemble similar sensitivity and are resilient against a wide range of inferences in spatio-temporal domain. For the first time, a novel CR pruning technique is proposed to significantly improve the delay between successive CR submissions. We carry out an experiment with a real dataset to show its effectiveness for sporadic, frequent, and continuous service use cases.
- 1 January 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 351-355
PPVC: Privacy Preserving Voronoi Cell for location-based services
The proliferation of GPS-enabled mobile devices has made location-based services (LBSs) very popular in mobile networks and protecting user's location information has become a critical issue of it. In a typical location-based service framework, the LBS requires the user to provide precise location information to assure better Quality of Services(QoS), while the user wants to hide this information as much as possible. This dilemma of privacy and quality of service trade-off has been studied in literature extensively. In this paper, we propose a spatial obfuscation framework, Privacy Preserving Voronoi Cell (PPVC) based on Voronoi diagram. In this framework user's region of interest (ROI) is divided into n sectors and each sector is concealed with an irregular quadrilateral, generated from a n-gon Voronoi cell and user's location is confounded within a convex region called Anonymity Zone. We evaluate PPVC with simulated environment, showing the efficiency and efficacy of the proposed framework. Finally, we implement it on Android phone with a user centric privacy scale.
- 1 January 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 351-355
PPVC: Privacy Preserving Voronoi Cell for location-based services
The proliferation of GPS-enabled mobile devices has made location-based services (LBSs) very popular in mobile networks and protecting user's location information has become a critical issue of it. In a typical location-based service framework, the LBS requires the user to provide precise location information to assure better Quality of Services(QoS), while the user wants to hide this information as much as possible. This dilemma of privacy and quality of service trade-off has been studied in literature extensively. In this paper, we propose a spatial obfuscation framework, Privacy Preserving Voronoi Cell (PPVC) based on Voronoi diagram. In this framework user's region of interest (ROI) is divided into n sectors and each sector is concealed with an irregular quadrilateral, generated from a n-gon Voronoi cell and user's location is confounded within a convex region called Anonymity Zone. We evaluate PPVC with simulated environment, showing the efficiency and efficacy of the proposed framework. Finally, we implement it on Android phone with a user centric privacy scale.
- 1 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 107-112
FRORSS: Fast result object retrieval using similarity search on cloud
This paper involves a cloud computing environment in which the data owner out sources the similarity search service to a third party service provider. The user provides an example query to the server to retrieve similar data. Privacy of the outsourced data is important because they may be sensitive, valuable or confidential data. The data should be made available to the authorized client/client groups, but not to be revealed to the service provider in which the data is stored. Given this scenario, the paper presents a technique called FRORSS which has build phase, data transformation and search phase. The build phase is about uploading the data; the data transformation phase transforms the data before submitting it to the service provider for similarity queries on the transformed data; search phase involves searching similar object with respect to query object. Experiments have been carried out on real data sets which exhibits that the proposed work is capable of providing privacy and achieving accuracy at a lower value of result measure in comparision with FDH [1].
- 1 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 107-112
FRORSS: Fast result object retrieval using similarity search on cloud
This paper involves a cloud computing environment in which the data owner out sources the similarity search service to a third party service provider. The user provides an example query to the server to retrieve similar data. Privacy of the outsourced data is important because they may be sensitive, valuable or confidential data. The data should be made available to the authorized client/client groups, but not to be revealed to the service provider in which the data is stored. Given this scenario, the paper presents a technique called FRORSS which has build phase, data transformation and search phase. The build phase is about uploading the data; the data transformation phase transforms the data before submitting it to the service provider for similarity queries on the transformed data; search phase involves searching similar object with respect to query object. Experiments have been carried out on real data sets which exhibits that the proposed work is capable of providing privacy and achieving accuracy at a lower value of result measure in comparision with FDH [1].
- 19 April 2016
- Published by Taylor & Francis
- p. 730-737
- Localization in 3D Wireless Sensor Networks Based on Geometric Computation
- 19 April 2016
- Published by Taylor & Francis
- p. 730-737
- Localization in 3D Wireless Sensor Networks Based on Geometric Computation
- 1 March 1995
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 12 (1) , 87-100
Robot reachability problem: A nonlinear optimization approach
- 1 March 1995
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 12 (1) , 87-100
Robot reachability problem: A nonlinear optimization approach