Rashmikiran Pandey
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rashmikiran Pandey has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Mrinal Pandey
Faculty of Radio and Computer Technology, Moscow Institute of Physics & Technology, Moscow, Russia
8 shared publications - Alexey Nikolaevich Nazarov
Federal Research Center Computer Science and Control, Russian Academy of Science, Moscow, Russia
7 shared publications - Alexey Nikolaevich Nazarov
Federal Research Center Computer Science and Control of Russian Academy of Sciences
2 shared publications Mrinal Pandey
Moskovskij fiziko-tehniceskij institut nacional'nyj issledovatel'skij universitet
2 shared publicationsAlexey Nazarov
Russian Academy of Sciences, Moscow, Russia
1 shared publication
Latest Publications
- Open Access
- 7 April 2026
- Published by Springer Nature in International Journal of Information Security
- Vol. 25 (3) , 78
Correction: Modeling information warfare in scale-free networks: analysis of propagation and counter-propagation dynamics
- 7 April 2026
- Published by Springer Nature in International Journal of Information Security
- Vol. 25 (3) , 78
Open AccessCorrection: Modeling information warfare in scale-free networks: analysis of propagation and counter-propagation dynamics
- 27 October 2025
- Published by Springer Nature in International Journal of Information Security
- Vol. 24 (6) , 1-17
Modeling information warfare in scale-free networks: analysis of propagation and counter-propagation dynamics
- 27 October 2025
- Published by Springer Nature in International Journal of Information Security
- Vol. 24 (6) , 1-17
Modeling information warfare in scale-free networks: analysis of propagation and counter-propagation dynamics
- Open Access
- 1 October 2024
- Published by ITMO University in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
- Vol. 24 (5) , 788
Enhanced anomaly detection in network security: a comprehensive ensemble approach
Detection and handling of anomalous behavior in the network systems are peremptory efforts to ensure security for vulnerable infrastructures amidst the dynamic context of cybersecurity. In this paper, we propose an ensemble machine learning model architecture that leverages the strengths of XGBoost, Gradient Boosting, Random Forest, and Support Vector Machine models to identify anomalies in the dataset. This method utilizes an ensemble of these models with weighted voting based on accuracy to enhance anomaly detection for robust and adaptive real-world network security. The proposed ensemble learning model is evaluated on standard metrics and demonstrates exceptional efficacy, achieving an impressive accuracy of 99.68 % on NSL KDD dataset. This remarkable performance extends the model prowess in discerning anomalies within network traffic showcasing its potential as a robust tool for enhancing cybersecurity measures against evolving threats.
- 1 October 2024
- Published by ITMO University in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
- Vol. 24 (5) , 788
Open AccessEnhanced anomaly detection in network security: a comprehensive ensemble approach
Detection and handling of anomalous behavior in the network systems are peremptory efforts to ensure security for vulnerable infrastructures amidst the dynamic context of cybersecurity. In this paper, we propose an ensemble machine learning model architecture that leverages the strengths of XGBoost, Gradient Boosting, Random Forest, and Support Vector Machine models to identify anomalies in the dataset. This method utilizes an ensemble of these models with weighted voting based on accuracy to enhance anomaly detection for robust and adaptive real-world network security. The proposed ensemble learning model is evaluated on standard metrics and demonstrates exceptional efficacy, achieving an impressive accuracy of 99.68 % on NSL KDD dataset. This remarkable performance extends the model prowess in discerning anomalies within network traffic showcasing its potential as a robust tool for enhancing cybersecurity measures against evolving threats.
- 14 June 2024
- Published by Springer Nature
- p. 87-99
Dynamic Multihead Attention for Enhancing Neural Machine Translation Performance
- 14 June 2024
- Published by Springer Nature
- p. 87-99
Dynamic Multihead Attention for Enhancing Neural Machine Translation Performance
- 23 April 2024
- Published by Springer Nature
- p. 601-618
Advancing Network Anomaly Detection: Comparative Analysis of Machine Learning Models
- 23 April 2024
- Published by Springer Nature
- p. 601-618
Advancing Network Anomaly Detection: Comparative Analysis of Machine Learning Models
- Open Access
- 20 February 2024
- Published by Springer Nature in Research Square
Modeling Information Warfare in Scale-Free Networks: Analysis of Propagation and Counter-Propagation Dynamics
In an era where information's rapid dissemination profoundly impacts society, this study introduces a comprehensive model examining information warfare dynamics within a scale-free network. Emphasizing the propagation and counter-propagation processes, our model intricately captures interactions among network nodes and their attributed statuses. Constructing a scale-free network via the Barabasi-Albert model, we simulate an information dissemination environment, attributing nodes as Informed or Unversed to mirror the diversity within the network. The transmission probability, contingent on node attributes, governs the information propagation process, while a reinforcement mechanism factors in the higher susceptibility of Unversed nodes to reinfection. Introducing a counter-propagation process to recover infected nodes, recovery probabilities are tailored based on node literacy status, potentially enhancing intervention effectiveness. Extensive simulations scrutinize the dynamics of information warfare, investigating parameters like transmission and recovery probabilities, and network topology's influence on information spread and counter-propagation success. This study evaluates defender and attacker accuracy, unveiling varied strategy effectiveness. The accuracy of the defender, which measures the rate at which nodes recover and align with their actual literacy attributes, was found to be 66.7% in defender dominant state and accuracy of attacker was 81.9% in attacker dominant state. Our findings illuminate the intricate dynamics of information warfare, underscoring the pivotal role of literacy status and proposing strategies to bolster defender accuracy.
- 20 February 2024
- Published by Springer Nature in Research Square
Open AccessModeling Information Warfare in Scale-Free Networks: Analysis of Propagation and Counter-Propagation Dynamics
In an era where information's rapid dissemination profoundly impacts society, this study introduces a comprehensive model examining information warfare dynamics within a scale-free network. Emphasizing the propagation and counter-propagation processes, our model intricately captures interactions among network nodes and their attributed statuses. Constructing a scale-free network via the Barabasi-Albert model, we simulate an information dissemination environment, attributing nodes as Informed or Unversed to mirror the diversity within the network. The transmission probability, contingent on node attributes, governs the information propagation process, while a reinforcement mechanism factors in the higher susceptibility of Unversed nodes to reinfection. Introducing a counter-propagation process to recover infected nodes, recovery probabilities are tailored based on node literacy status, potentially enhancing intervention effectiveness. Extensive simulations scrutinize the dynamics of information warfare, investigating parameters like transmission and recovery probabilities, and network topology's influence on information spread and counter-propagation success. This study evaluates defender and attacker accuracy, unveiling varied strategy effectiveness. The accuracy of the defender, which measures the rate at which nodes recover and align with their actual literacy attributes, was found to be 66.7% in defender dominant state and accuracy of attacker was 81.9% in attacker dominant state. Our findings illuminate the intricate dynamics of information warfare, underscoring the pivotal role of literacy status and proposing strategies to bolster defender accuracy.
- 30 December 2023
- Published by Springer Nature in International Journal of Information Technology
- Vol. 16 (3) , 1527-1538
Modelling information warfare dynamics to counter propaganda using a nonlinear differential equation with a PINN-based learning approach
- 30 December 2023
- Published by Springer Nature in International Journal of Information Technology
- Vol. 16 (3) , 1527-1538
Modelling information warfare dynamics to counter propaganda using a nonlinear differential equation with a PINN-based learning approach
- Open Access
- 29 July 2023
- Published by Wiley
Modelling Information Warfare Dynamics to Counter Propaganda using a Nonlinear Differential Equation with a PINN-based Learning Approach
This research work presents a novel approach to combat propaganda and misinformation in the context of information warfare through the integration of a modified logistic differential equation, a Physics-Informed Neural Network (PINN), and a comprehensive parameter sensitivity analysis. The study leverages the LIAR dataset, which offers a diverse range of labelled statements reflecting real-world political discourse, making it an ideal foundation for capturing the complexities of propaganda dynamics. The modified logistic equation, incorporating parameters such as spread rate (α), decay rate (β), and growth rate (γ), is employed to capture the intricate dynamics of information spread and adoption. The PINN model uses domain knowledge and data to estimate the underlying dynamics and unknown parameters of the logistic equation. This allows for highly accurate classification and analysis of propaganda spread. Thereafter, a parameter sensitivity analysis is conducted under different attacker intensities, categorized as aggressive, neutral, and non-aggressive. Varying population sizes are considered to assess the implications of different parameter combinations. The results reveal the significant influence of the spread rate parameter (α), highlighting the aggressiveness of the attacker’s propaganda dissemination in information warfare scenarios. Furthermore, the proposed PINN-based model’s performance is evaluated against two benchmark models: a Term Frequency-Inverse Document Frequency (TF- IDF) model and the random forest classifier. The PINN model achieved an impressive accuracy rate of 97.32% on the LIAR dataset, outperforming both the TF-IDF model (93.87%) and the random forest classifier (95%). This demonstrates the superior predictive power and effectiveness of the PINN model in capturing the complexities of information spread in the realm of propaganda and misinformation. This research lays down a robust groundwork for research aimed at combating propaganda and pushing the boundaries of information warfare. It achieves this by validating the efficacy of the proposed model and showcasing its superiority when compared to existing benchmark models. The comprehensive parameter sensitivity analysis further enhances the understanding of the system’s behavior and offers insights into the impact of varying parameter values.
- 29 July 2023
- Published by Wiley
Open AccessModelling Information Warfare Dynamics to Counter Propaganda using a Nonlinear Differential Equation with a PINN-based Learning Approach
This research work presents a novel approach to combat propaganda and misinformation in the context of information warfare through the integration of a modified logistic differential equation, a Physics-Informed Neural Network (PINN), and a comprehensive parameter sensitivity analysis. The study leverages the LIAR dataset, which offers a diverse range of labelled statements reflecting real-world political discourse, making it an ideal foundation for capturing the complexities of propaganda dynamics. The modified logistic equation, incorporating parameters such as spread rate (α), decay rate (β), and growth rate (γ), is employed to capture the intricate dynamics of information spread and adoption. The PINN model uses domain knowledge and data to estimate the underlying dynamics and unknown parameters of the logistic equation. This allows for highly accurate classification and analysis of propaganda spread. Thereafter, a parameter sensitivity analysis is conducted under different attacker intensities, categorized as aggressive, neutral, and non-aggressive. Varying population sizes are considered to assess the implications of different parameter combinations. The results reveal the significant influence of the spread rate parameter (α), highlighting the aggressiveness of the attacker’s propaganda dissemination in information warfare scenarios. Furthermore, the proposed PINN-based model’s performance is evaluated against two benchmark models: a Term Frequency-Inverse Document Frequency (TF- IDF) model and the random forest classifier. The PINN model achieved an impressive accuracy rate of 97.32% on the LIAR dataset, outperforming both the TF-IDF model (93.87%) and the random forest classifier (95%). This demonstrates the superior predictive power and effectiveness of the PINN model in capturing the complexities of information spread in the realm of propaganda and misinformation. This research lays down a robust groundwork for research aimed at combating propaganda and pushing the boundaries of information warfare. It achieves this by validating the efficacy of the proposed model and showcasing its superiority when compared to existing benchmark models. The comprehensive parameter sensitivity analysis further enhances the understanding of the system’s behavior and offers insights into the impact of varying parameter values.
- Open Access
- 10 July 2023
- Published by Springer Nature in Research Square
Modelling the Dynamics of Information Warfare: An Attacker-Defender Scenario Using Lotka-Volterra Equations
The dynamics of information warfare in an attacker-defender scenario pose significant challenges in today's digital age. To address these challenges, this research proposes a model based on the modified Lotka-Volterra equations, originally developed for predator-prey interactions in ecological systems, to analyze and simulate the population dynamics of attackers and defenders in information warfare. The model captures the growth, interaction, and feedback loop between the attacker and defender populations, allowing for a comprehensive understanding of their dynamics over time. In this model, the attacker equation incorporates parameters for the attacker's growth rate and the impact of defenders on attackers. Similarly, the defender equation considers the defender's natural decline rate and the influence of attackers on defenders. By discretizing time into small intervals and employing Euler's method, the model enables real-time simulation of the attacker-defender scenario. The simulation spans a time interval of 100 units, providing insights into the population dynamics and equilibrium points of the attacker and defender populations. The research findings highlight the model's effectiveness in capturing the dynamics of information warfare. The simulation results showcase the initial growth of the attacker population, followed by a decline as defenders implement effective countermeasures. Conversely, the defender population grows and stabilizes as their defensive capabilities improve. The research contributes to the growing body of knowledge in information warfare and provides insights for the development of robust defence strategies.
- 10 July 2023
- Published by Springer Nature in Research Square
Open AccessModelling the Dynamics of Information Warfare: An Attacker-Defender Scenario Using Lotka-Volterra Equations
The dynamics of information warfare in an attacker-defender scenario pose significant challenges in today's digital age. To address these challenges, this research proposes a model based on the modified Lotka-Volterra equations, originally developed for predator-prey interactions in ecological systems, to analyze and simulate the population dynamics of attackers and defenders in information warfare. The model captures the growth, interaction, and feedback loop between the attacker and defender populations, allowing for a comprehensive understanding of their dynamics over time. In this model, the attacker equation incorporates parameters for the attacker's growth rate and the impact of defenders on attackers. Similarly, the defender equation considers the defender's natural decline rate and the influence of attackers on defenders. By discretizing time into small intervals and employing Euler's method, the model enables real-time simulation of the attacker-defender scenario. The simulation spans a time interval of 100 units, providing insights into the population dynamics and equilibrium points of the attacker and defender populations. The research findings highlight the model's effectiveness in capturing the dynamics of information warfare. The simulation results showcase the initial growth of the attacker population, followed by a decline as defenders implement effective countermeasures. Conversely, the defender population grows and stabilizes as their defensive capabilities improve. The research contributes to the growing body of knowledge in information warfare and provides insights for the development of robust defence strategies.