Eram Fatima Siddiqui
Research Subjects
Eram Fatima Siddiqui has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
A. E. M. Eljialy
Prince Sattam Bin Abdulaziz University, Saudi Arabia
1 shared publication- Abu Taha Zamani
Department of Computer Science, Faculty of Science, Northern Border University, Arar, Saudi Arabia
1 shared publication - Amina Salhi
Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh, Saudi Arabia
1 shared publication - Hikmat A. M. Abdeljaber
Department of Computer Science, Faculty of Information Technology, Applied Science Private University, Amman, Jordan
1 shared publication - Mohammad Faisal
Integral University
1 shared publication - Mohd Haleem
Department of Computer Science, Era University, Lucknow, Uttar Pradesh, INDIA
1 shared publication
Latest Publications
- Open Access
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 170235-170257
A Multi-Layered AI-Driven Cybersecurity Architecture: Integrating Entropy Analytics, Fuzzy Reasoning, Game Theory, and Multi-Agent Reinforcement Learning for Adaptive Threat Defense
In the face of increasingly sophisticated cyberattacks, including adaptive adversaries and stealthy anomalies, key features of defense mechanisms should be effective, interpretable, and theoretically rooted. Conventional intrusion detection systems are typically based on a single-paradigm machine learning model which can be effective (because it is optimized for conditions), but fail in generalizability and falling back on an explanation of its prediction. This paper outlines a multi-layered AI-enabled cyber defense framework that integrates entropy analytics, fuzzy inference, game-theoretic defense, and multi-agent reinforcement learning (MARL) inside a closed-loop adaptive architecture. In its simplest form, the novelty of the paper is that, four functional paradigms - uncertainty quantification, interpretability, strategic adversarial thinking, and live policy adaptation - are placed into a single coherent system. The framework operates as sequential and feedback salients - entropy analytics quantify the uncertainty in are states, fuzzy inference end maps the uncertainty into qualitative decision rules, game theory shapes defender - attacker towards equilibrium strategies, and MARL dynamically updates those strategies for convergence and long term adaptation. The empirical work on appropriate benchmark intrusion detection datasets consistently Thoutperformed baseline systems including the DDN, Fed-ID, AG-IDS, DL-FL systems producing a 6-12% increase in detection accuracy, lower false positive rates from non-intrusions, and a faster convergence, with adversarial examples across multiple epochs. Also, practical case studies reveal a level of improved explainability in threat classification and anomaly detection, which equates to practical interpretability for security analysts from the framework. The major contributions of the work are threefold: (i) an integrated multi-layered AI-based cybersecurity framework, (ii) theoretical robustness results in bounded adversarial models, and (iii) performance and interpretability form the systematic empirical evaluations over multiple datasets.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 170235-170257
Open AccessA Multi-Layered AI-Driven Cybersecurity Architecture: Integrating Entropy Analytics, Fuzzy Reasoning, Game Theory, and Multi-Agent Reinforcement Learning for Adaptive Threat Defense
In the face of increasingly sophisticated cyberattacks, including adaptive adversaries and stealthy anomalies, key features of defense mechanisms should be effective, interpretable, and theoretically rooted. Conventional intrusion detection systems are typically based on a single-paradigm machine learning model which can be effective (because it is optimized for conditions), but fail in generalizability and falling back on an explanation of its prediction. This paper outlines a multi-layered AI-enabled cyber defense framework that integrates entropy analytics, fuzzy inference, game-theoretic defense, and multi-agent reinforcement learning (MARL) inside a closed-loop adaptive architecture. In its simplest form, the novelty of the paper is that, four functional paradigms - uncertainty quantification, interpretability, strategic adversarial thinking, and live policy adaptation - are placed into a single coherent system. The framework operates as sequential and feedback salients - entropy analytics quantify the uncertainty in are states, fuzzy inference end maps the uncertainty into qualitative decision rules, game theory shapes defender - attacker towards equilibrium strategies, and MARL dynamically updates those strategies for convergence and long term adaptation. The empirical work on appropriate benchmark intrusion detection datasets consistently Thoutperformed baseline systems including the DDN, Fed-ID, AG-IDS, DL-FL systems producing a 6-12% increase in detection accuracy, lower false positive rates from non-intrusions, and a faster convergence, with adversarial examples across multiple epochs. Also, practical case studies reveal a level of improved explainability in threat classification and anomaly detection, which equates to practical interpretability for security analysts from the framework. The major contributions of the work are threefold: (i) an integrated multi-layered AI-based cybersecurity framework, (ii) theoretical robustness results in bounded adversarial models, and (iii) performance and interpretability form the systematic empirical evaluations over multiple datasets.
- 18 April 2025
- Published by IGI Global Scientific Publishing
- p. 117-156
Techniques for Combining Data From Multiple Sensors
Quality data delivery and communication in an ultra-latent and real-time manner are some its stringent requirements for Internet of Things (IoT). In IoT, raw data is sensed from real-world and transformed into a usable form. Collection of this raw data from multiple sensors as compared to a single one, it is found to be of better quality and high accuracy. This method of collecting same type of data is called data or sensor fusion. In this paper a meticulous study on the role of data fusion have been done with respect to its application with Internet of Things, Machine Learning (ML) and Mobile Edge Computing (MEC).This paper discusses the mechanism, multi-modal fusion techniques, past proposed standard data fusion models and related issues, along with its application with support of machine learning and Edge Computing Lastly, the paper discusses about the concept of Edge Intelligence to deliver reliable outputs with future directions and issues.
- 18 April 2025
- Published by IGI Global Scientific Publishing
- p. 117-156
Techniques for Combining Data From Multiple Sensors
Quality data delivery and communication in an ultra-latent and real-time manner are some its stringent requirements for Internet of Things (IoT). In IoT, raw data is sensed from real-world and transformed into a usable form. Collection of this raw data from multiple sensors as compared to a single one, it is found to be of better quality and high accuracy. This method of collecting same type of data is called data or sensor fusion. In this paper a meticulous study on the role of data fusion have been done with respect to its application with Internet of Things, Machine Learning (ML) and Mobile Edge Computing (MEC).This paper discusses the mechanism, multi-modal fusion techniques, past proposed standard data fusion models and related issues, along with its application with support of machine learning and Edge Computing Lastly, the paper discusses about the concept of Edge Intelligence to deliver reliable outputs with future directions and issues.
- Open Access
- 18 January 2024
- Published by Elsevier in Measurement: Sensors
- Vol. 32
A decision tree approach for enhancing real-time response in exigent healthcare unit using edge computing
- 18 January 2024
- Published by Elsevier in Measurement: Sensors
- Vol. 32
Open AccessA decision tree approach for enhancing real-time response in exigent healthcare unit using edge computing