Sahar Ebadinezhad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sahar Ebadinezhad has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Assem Alhawari
Department of Computer Information Systems, Near East University, Near East Boulevard, 99138 Nicosia, Northern Cyprus (TRNC), Turkey
3 shared publications Ibrahim Khalaf Hussein
Near East University
2 shared publicationsNwabueze Kenneth Osemeha
Near East University,Software Engineering Department,Nicosia,North Cyprus
2 shared publications- Oluwaseun Priscilla Olawale
Near East University
2 shared publications Abdiwahab Yousuf Abdillahi
Near East University,Department of Computer Information Systems,Nicosia,Cyprus,99138
1 shared publicationAhmad Shoaib Mayar
Near East University,Department of Computer Information Systems,Nicosia,Cyprus,99138
1 shared publication
Latest Publications
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Optimizing Digital Identity Resilience: A Systematic Literature Review of Adversarial Generative AI Using GANs and LLMs
Specifically, this systematic literature review (SLR) focuses on adversarial Generative Artificial Intelligence (AI) and digital identity resilience, a key area of focus for intelligent systems security domains. As Generative Adversarial Networks (GANs) and Large Language Models (LLMs) are evolving more rapidly, however, they can also pose dual-use challenges: they allow for complex identity threats and open up new paths for robust defense. Using SLR criteria, the current study conducts a systematic study on adversarial approaches to digital identities and evaluates the proposed defensive strategies for detection and mitigation. An expansive taxonomy of datasets, modalities, and evaluation measures includes system robustness, explainability, and generalization, to name a few. This paper provides data on the key research gaps in identity resilience for the automated environment through use of the most current literature to expose this aspect. The results are expected to provide a foundation of how to improve on defensive AI architectures in this field which would eventually pave the way for future research towards secure human-computer interaction and resilient autonomous systems.
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Optimizing Digital Identity Resilience: A Systematic Literature Review of Adversarial Generative AI Using GANs and LLMs
Specifically, this systematic literature review (SLR) focuses on adversarial Generative Artificial Intelligence (AI) and digital identity resilience, a key area of focus for intelligent systems security domains. As Generative Adversarial Networks (GANs) and Large Language Models (LLMs) are evolving more rapidly, however, they can also pose dual-use challenges: they allow for complex identity threats and open up new paths for robust defense. Using SLR criteria, the current study conducts a systematic study on adversarial approaches to digital identities and evaluates the proposed defensive strategies for detection and mitigation. An expansive taxonomy of datasets, modalities, and evaluation measures includes system robustness, explainability, and generalization, to name a few. This paper provides data on the key research gaps in identity resilience for the automated environment through use of the most current literature to expose this aspect. The results are expected to provide a foundation of how to improve on defensive AI architectures in this field which would eventually pave the way for future research towards secure human-computer interaction and resilient autonomous systems.
- Open Access
- 18 May 2026
- Published by MDPI AG in Electronics
- Vol. 15 (10) , 2167
AI-Driven Rule-Based Feature Scoring for Explainable and Adversarially Robust Android Malware Detection
The rapidly evolving Android malware that employs obfuscation and adversarial techniques has become a critical challenge for cybersecurity detection systems. This study introduces RFS-MD, short for Rule-based Feature Scoring for Malware Detection, a framework that builds explainability and adversarial defense into the detection pipeline by deriving feature importance scores directly from classification association rules. Experiments across several machine learning (ML) and deep learning (DL) classifiers on a balanced static feature dataset demonstrate that scored features improved recall across all six evaluated classifiers under cross-validation, with statistically significant accuracy and recall gains confirmed in four of the six. Under-tuned hyperparameter configurations, scored features consistently outperformed non-scored features across all classifiers. Furthermore, RFS-MD enhanced model robustness against adversarial attacks, reducing attack success rates and maintaining positive recall gains over baseline models. A rule-based explainability approach (RXAI) is introduced to generate transparent and human-readable model explanations; fidelity analysis confirms that RXAI captures interacting malicious feature patterns aligned with classifier decisions. Overall, the findings show that rule-based feature scoring offers a single, unified way to tackle accuracy, robustness, and explainability in Android malware detection simultaneously, contributing to trustworthy AI-driven cybersecurity solutions.
- 18 May 2026
- Published by MDPI AG in Electronics
- Vol. 15 (10) , 2167
Open AccessAI-Driven Rule-Based Feature Scoring for Explainable and Adversarially Robust Android Malware Detection
The rapidly evolving Android malware that employs obfuscation and adversarial techniques has become a critical challenge for cybersecurity detection systems. This study introduces RFS-MD, short for Rule-based Feature Scoring for Malware Detection, a framework that builds explainability and adversarial defense into the detection pipeline by deriving feature importance scores directly from classification association rules. Experiments across several machine learning (ML) and deep learning (DL) classifiers on a balanced static feature dataset demonstrate that scored features improved recall across all six evaluated classifiers under cross-validation, with statistically significant accuracy and recall gains confirmed in four of the six. Under-tuned hyperparameter configurations, scored features consistently outperformed non-scored features across all classifiers. Furthermore, RFS-MD enhanced model robustness against adversarial attacks, reducing attack success rates and maintaining positive recall gains over baseline models. A rule-based explainability approach (RXAI) is introduced to generate transparent and human-readable model explanations; fidelity analysis confirms that RXAI captures interacting malicious feature patterns aligned with classifier decisions. Overall, the findings show that rule-based feature scoring offers a single, unified way to tackle accuracy, robustness, and explainability in Android malware detection simultaneously, contributing to trustworthy AI-driven cybersecurity solutions.
- Open Access
- 21 April 2026
- Published by MDPI AG in Preprints.org
AI-Driven Rule-Based Feature Scoring for Explainable and Adversarially Robust Android Malware Detection
The rapidly evolving Android malware that employs obfuscation and adversarial techniques has become a challenge for cybersecurity malware detection systems. This study proposes an explainable adversarial defense framework, namely RFS-MD (Rule-based Feature Scoring for Malware Detection), that integrates feature importance scores derived from classification association rules, along with the rules themselves, into malware detection models to enhance detection performance, robustness, and explainability. Several experiments were performed on a balanced static feature dataset across several machine learning (ML) and deep learning (DL) classifiers to demonstrate that scored features consistently improved. accuracy and recall, compared to non-scored features under both default and tuned parameters across all classifiers. Furthermore, RFS-MD enhanced the model’s robustness against adversarial attacks, reducing attack success rates (ASR) and maintaining a positive recalgain compared to baseline models. In addition, a rule-based explanability approach (RXAI) is introduced to generate transparent and human-readable explanations of the model decisions, where the fidelity analysis confirms that RXAI captures interacting malicious feature patterns that align with classifier results. Overall, the results indicate that the rule-based feature scoring technique, along with rules, presents an effective approach towards android malware detection systems that simultaneously improve accuracy, robustness, and explainability, contributing to trustworthy AI-driven cybersecurity solutions.
- 21 April 2026
- Published by MDPI AG in Preprints.org
Open AccessAI-Driven Rule-Based Feature Scoring for Explainable and Adversarially Robust Android Malware Detection
The rapidly evolving Android malware that employs obfuscation and adversarial techniques has become a challenge for cybersecurity malware detection systems. This study proposes an explainable adversarial defense framework, namely RFS-MD (Rule-based Feature Scoring for Malware Detection), that integrates feature importance scores derived from classification association rules, along with the rules themselves, into malware detection models to enhance detection performance, robustness, and explainability. Several experiments were performed on a balanced static feature dataset across several machine learning (ML) and deep learning (DL) classifiers to demonstrate that scored features consistently improved. accuracy and recall, compared to non-scored features under both default and tuned parameters across all classifiers. Furthermore, RFS-MD enhanced the model’s robustness against adversarial attacks, reducing attack success rates (ASR) and maintaining a positive recalgain compared to baseline models. In addition, a rule-based explanability approach (RXAI) is introduced to generate transparent and human-readable explanations of the model decisions, where the fidelity analysis confirms that RXAI captures interacting malicious feature patterns that align with classifier results. Overall, the results indicate that the rule-based feature scoring technique, along with rules, presents an effective approach towards android malware detection systems that simultaneously improve accuracy, robustness, and explainability, contributing to trustworthy AI-driven cybersecurity solutions.
- Open Access
Empowering IoV Security: A Novel Secure Cryptographic Algorithm (OpCKEE) for Network Protection in Connected Vehicles
According to Fortune Business Insights, the market share of the Internet of Vehicless is expected to grow from USD 95.62 billion in 2021 to USD 369.61 billion in 2028, at a compound annual growth rate of 21.4%. However, the Internet of Vehicles system still faces several challenges, including regulation, scalability, data management, connectivity, interoperability, privacy, and security. To improve communication security within the Internet of Vehicle system, we have implemented a secure cryptographic algorithm called Optimized Certificateless Key-Encapsulated Encryption, resulting from a fusion of the key-insulated cryptosystem and the cryptographic key-encapsulated mechanism. The formal security analysis of our algorithm using the AVISPA version 1.1 software shows us that our protocol is safe. Informal analysis shows that our algorithm ensures authenticity, confidentiality, integrity, and non-repudiation and resists several other attacks. Our algorithm’s computational and communicational costs are slightly better than those at which it inherits the functionalities.
Open AccessEmpowering IoV Security: A Novel Secure Cryptographic Algorithm (OpCKEE) for Network Protection in Connected Vehicles
According to Fortune Business Insights, the market share of the Internet of Vehicless is expected to grow from USD 95.62 billion in 2021 to USD 369.61 billion in 2028, at a compound annual growth rate of 21.4%. However, the Internet of Vehicles system still faces several challenges, including regulation, scalability, data management, connectivity, interoperability, privacy, and security. To improve communication security within the Internet of Vehicle system, we have implemented a secure cryptographic algorithm called Optimized Certificateless Key-Encapsulated Encryption, resulting from a fusion of the key-insulated cryptosystem and the cryptographic key-encapsulated mechanism. The formal security analysis of our algorithm using the AVISPA version 1.1 software shows us that our protocol is safe. Informal analysis shows that our algorithm ensures authenticity, confidentiality, integrity, and non-repudiation and resists several other attacks. Our algorithm’s computational and communicational costs are slightly better than those at which it inherits the functionalities.
- 17 January 2026
- Published by Springer Nature
- p. 370-379
Securing AI-Driven Biometric Authentication Systems: Cryptographic Techniques for Protecting Sensitive User Data
- 17 January 2026
- Published by Springer Nature
- p. 370-379
Securing AI-Driven Biometric Authentication Systems: Cryptographic Techniques for Protecting Sensitive User Data
- 17 January 2026
- Published by Springer Nature
- p. 248-263
Secure and Sustainable AI-Driven Virtual Healthcare Assistants: Privacy-Preserving NLP for Future-Ready Patient Care
- 17 January 2026
- Published by Springer Nature
- p. 248-263
Secure and Sustainable AI-Driven Virtual Healthcare Assistants: Privacy-Preserving NLP for Future-Ready Patient Care
- 17 January 2026
- Published by Springer Nature
- p. 12-29
Securing 5G Network Slicing: A Hybrid Machine Learning Approach for DDoS Threat Detection and Performance Evaluation
- 17 January 2026
- Published by Springer Nature
- p. 12-29
Securing 5G Network Slicing: A Hybrid Machine Learning Approach for DDoS Threat Detection and Performance Evaluation
- 1 January 2026
- Published by IACSIT Press in International Journal of Computer Theory and Engineering
- Vol. 18 (4) , 243-252
Machine Learning for Predictive Base Station Sleep Modes to Enhance 5G Greenness
The rapid deployment of 5G mobile communications has drastically increased the energy consumption of radio access networks, and Base Stations (BSs) account for 60%–80% of network energy consumption. This work presents a low-complexity predictive base station sleep mode framework based on Long Short-Term Memory (LSTM) traffic forecasting and a threshold-based control loop. It is based on proactive forecasting that is able to automatically transition BSs to sleep mode during low-demand state transitions in the predicted low-demand periods of the network, thereby minimizing frequent state-switching overhead and extending low-power intervals. Based on the real-world Telecom Italia Mobile Big Data Challenge data set (Milan and Trentino), our framework realized energy savings of up to 45.8% over the always-on baseline and 32.0% over the reactive baseline. Most importantly, our system does not breach Quality of Experience (QoE) service at the optimal 100 Mbps speed, and it requires much less computational effort than state-of-the-art reinforcement learning structures. A multi-objective sensitivity analysis presents the Pareto front to capture energy efficiency and service reliability. These results indicate that the lightweight predictive engineering frameworks can be a very practical and scalable way to manage the green 5G networks.
- 1 January 2026
- Published by IACSIT Press in International Journal of Computer Theory and Engineering
- Vol. 18 (4) , 243-252
Machine Learning for Predictive Base Station Sleep Modes to Enhance 5G Greenness
The rapid deployment of 5G mobile communications has drastically increased the energy consumption of radio access networks, and Base Stations (BSs) account for 60%–80% of network energy consumption. This work presents a low-complexity predictive base station sleep mode framework based on Long Short-Term Memory (LSTM) traffic forecasting and a threshold-based control loop. It is based on proactive forecasting that is able to automatically transition BSs to sleep mode during low-demand state transitions in the predicted low-demand periods of the network, thereby minimizing frequent state-switching overhead and extending low-power intervals. Based on the real-world Telecom Italia Mobile Big Data Challenge data set (Milan and Trentino), our framework realized energy savings of up to 45.8% over the always-on baseline and 32.0% over the reactive baseline. Most importantly, our system does not breach Quality of Experience (QoE) service at the optimal 100 Mbps speed, and it requires much less computational effort than state-of-the-art reinforcement learning structures. A multi-objective sensitivity analysis presents the Pareto front to capture energy efficiency and service reliability. These results indicate that the lightweight predictive engineering frameworks can be a very practical and scalable way to manage the green 5G networks.