Farah Kandah
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
Farah Kandah has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Lalith Medury
Computer Science and Software Engineering, Auburn University, Auburn, AL, USA
4 shared publications - Brennan Huber
Computer Science and Engineering, University of Tennessee at Chattanooga,Chattanooga,TN
3 shared publications - Thilina Mendis
Computer Science and Software Engineering, Auburn University, Auburn, USA
3 shared publications Haofan Wang
Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA
2 shared publications- Haofan Wang
Auburn University
2 shared publications - Haofan Wang2 shared publications
Latest Publications
- 4 September 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
Counterfactual incremental defense against poisoning attacks
- 4 September 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
Counterfactual incremental defense against poisoning attacks
- 1 May 2026
- Published by Springer Nature
- p. 456-467
Explainable CAN Intrusion Detection via Feature Extraction
- 1 May 2026
- Published by Springer Nature
- p. 456-467
Explainable CAN Intrusion Detection via Feature Extraction
- 31 December 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 180
Knowledge distillation-based Multi-Optimization intrusion detection system
- 31 December 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 180
Knowledge distillation-based Multi-Optimization intrusion detection system
- 20 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (22) , 46878-46888
Unmasking IoT Devices: A Dynamic and Adaptive Classification Approach
The proliferation of IoT devices has revolutionized automation and connectivity across various industries. These devices rely extensively on wireless communication, enabling flexibility and real-time data exchange. The unique traffic patterns they produce, shaped by protocol usage, communication frequency, and data exchange behaviors allow for accurate device identification-based solely on network activity. Previous research on IoT device identification has shown promise but faces key limitations including scalability, requiring frequent retraining for new devices, and are computationally intensive and unsuitable for real-time use. Reliance on spoofable attributes like IP and MAC addresses, or documentation-based profiling, further reduces reliability. To overcome these limitations, this study introduces UMIoT, an adaptive and dynamic multi-classifier framework for IoT device identification. UMIoT is trained on packet-streams, assigns a dedicated classifier to each device, improving accuracy, scalability, and adaptability. Furthermore, UMIoT can efficiently detect the presence of new devices without misclassifying their traffic as belonging to existing devices based on a parameterized confidence-threshold metric. Our experimental results demonstrate that UMIoT achieves high identification accuracy, maintains a low prediction time, enables rapid training for new emerging devices in the network, and operates with minimal storage overhead. Additionally, the results highlight the superiority of the proposed framework against existing device identification approaches both in terms of device identification accuracy and performance metrics including prediction time, storage overhead, and new device training time. The framework is also shown to be resilient against adversarial threats including traffic padding, shaping, and MAC address alteration.
- 20 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (22) , 46878-46888
Unmasking IoT Devices: A Dynamic and Adaptive Classification Approach
The proliferation of IoT devices has revolutionized automation and connectivity across various industries. These devices rely extensively on wireless communication, enabling flexibility and real-time data exchange. The unique traffic patterns they produce, shaped by protocol usage, communication frequency, and data exchange behaviors allow for accurate device identification-based solely on network activity. Previous research on IoT device identification has shown promise but faces key limitations including scalability, requiring frequent retraining for new devices, and are computationally intensive and unsuitable for real-time use. Reliance on spoofable attributes like IP and MAC addresses, or documentation-based profiling, further reduces reliability. To overcome these limitations, this study introduces UMIoT, an adaptive and dynamic multi-classifier framework for IoT device identification. UMIoT is trained on packet-streams, assigns a dedicated classifier to each device, improving accuracy, scalability, and adaptability. Furthermore, UMIoT can efficiently detect the presence of new devices without misclassifying their traffic as belonging to existing devices based on a parameterized confidence-threshold metric. Our experimental results demonstrate that UMIoT achieves high identification accuracy, maintains a low prediction time, enables rapid training for new emerging devices in the network, and operates with minimal storage overhead. Additionally, the results highlight the superiority of the proposed framework against existing device identification approaches both in terms of device identification accuracy and performance metrics including prediction time, storage overhead, and new device training time. The framework is also shown to be resilient against adversarial threats including traffic padding, shaping, and MAC address alteration.
- 23 June 2025
- Published by Springer Nature
- p. 469-483
Case-Based Reasoning with Diffusion Model for Ransomware Detection
- 23 June 2025
- Published by Springer Nature
- p. 469-483
Case-Based Reasoning with Diffusion Model for Ransomware Detection
- Open Access
- 23 June 2025
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 37 (5) , 1-18
MATADOR: a magic matrix-based framework for tamper detection and image recovery
- 23 June 2025
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 37 (5) , 1-18
Open AccessMATADOR: a magic matrix-based framework for tamper detection and image recovery
- Open Access
- 4 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 98888-98908
Navigating IoT Security: Architectures, Emerging Threats, and Adaptive Countermeasures
The Internet of Things (IoT) has revolutionized modern life, yet its interconnected nature poses significant security challenges. This survey investigates threats and countermeasures associated with IoT ecosystems, categorizes threats targeting network infrastructure, devices, and data security, and provides a taxonomy to understand vulnerabilities. By analyzing IoT architectures—including Cloud, Fog, and Edge—the study highlights how each architecture presents distinct vulnerabilities when integrated with IoT systems. It explores research on several countermeasures, including intrusion detection systems, secure authentication protocols, blockchain technology, and machine learning integration, evaluating both their advantages and limitations. Through a systematic reviewof recent literature, the survey identifies articles that contribute to IoT security understanding. The study advocates for lightweight, adaptable security measures that can be applied across diverse architectures and emphasizes the importance of standardized protocols through collaborative efforts among stakeholders. By mapping the current IoT security landscape, this survey guides future research and development toward a more secure and resilient IoT ecosystem, emphasizing the need for both innovation and standardization. Additionally, it critically evaluates the effectiveness of existing solutions and provides actionable insights into addressing the evolving security challenges within IoT environments.
- 4 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 98888-98908
Open AccessNavigating IoT Security: Architectures, Emerging Threats, and Adaptive Countermeasures
The Internet of Things (IoT) has revolutionized modern life, yet its interconnected nature poses significant security challenges. This survey investigates threats and countermeasures associated with IoT ecosystems, categorizes threats targeting network infrastructure, devices, and data security, and provides a taxonomy to understand vulnerabilities. By analyzing IoT architectures—including Cloud, Fog, and Edge—the study highlights how each architecture presents distinct vulnerabilities when integrated with IoT systems. It explores research on several countermeasures, including intrusion detection systems, secure authentication protocols, blockchain technology, and machine learning integration, evaluating both their advantages and limitations. Through a systematic reviewof recent literature, the survey identifies articles that contribute to IoT security understanding. The study advocates for lightweight, adaptable security measures that can be applied across diverse architectures and emphasizes the importance of standardized protocols through collaborative efforts among stakeholders. By mapping the current IoT security landscape, this survey guides future research and development toward a more secure and resilient IoT ecosystem, emphasizing the need for both innovation and standardization. Additionally, it critically evaluates the effectiveness of existing solutions and provides actionable insights into addressing the evolving security challenges within IoT environments.
- 24 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (11) , 16112-16128
Clustering-Based Intrusion Detection System Meets Multicritics Generative Adversarial Networks
Network security has continuously been a major focus of research and concern on a global scale. The Intrusion Detection System (IDS), as a crucial defensive measure against network attacks, has undergone multiple iterations and evolutions since its inception to adapt to the ever-changing network environment. Due to the widespread issue of data imbalance in network security datasets, a single machine learning or deep learning model often struggles to effectively handle different types of attacks. In this work, we propose a Multi-Critics Generative Adversarial Networks (GAN) Clustering-Based IDS (MCGC-IDS) model to address the issue of data imbalance. The quality of the generated data is analyzed using correlation heatmaps and PCA plots, which later is used to update the dataset that is utilized for feature extraction with autoencoders. Subsequently, CNN-LSTM models are employed to analyze clusters formed by the Weighted Fuzzy C-means (WFCM) clustering algorithm to achieve enhanced performance for the IDS system. This model is then compared with two existing models. The results indicate that while the GAN-generated data retains the original dataset distribution, it also addresses the issue of imbalance. Moreover, the subsequent multi-layered processing enables the overall model to more effectively handle various types of attacks. Finally, when this model is tested on a similar dataset, the UNSW-NB15, it continues to demonstrate superior performance, indicating its strong generalizability.
- 24 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (11) , 16112-16128
Clustering-Based Intrusion Detection System Meets Multicritics Generative Adversarial Networks
Network security has continuously been a major focus of research and concern on a global scale. The Intrusion Detection System (IDS), as a crucial defensive measure against network attacks, has undergone multiple iterations and evolutions since its inception to adapt to the ever-changing network environment. Due to the widespread issue of data imbalance in network security datasets, a single machine learning or deep learning model often struggles to effectively handle different types of attacks. In this work, we propose a Multi-Critics Generative Adversarial Networks (GAN) Clustering-Based IDS (MCGC-IDS) model to address the issue of data imbalance. The quality of the generated data is analyzed using correlation heatmaps and PCA plots, which later is used to update the dataset that is utilized for feature extraction with autoencoders. Subsequently, CNN-LSTM models are employed to analyze clusters formed by the Weighted Fuzzy C-means (WFCM) clustering algorithm to achieve enhanced performance for the IDS system. This model is then compared with two existing models. The results indicate that while the GAN-generated data retains the original dataset distribution, it also addresses the issue of imbalance. Moreover, the subsequent multi-layered processing enables the overall model to more effectively handle various types of attacks. Finally, when this model is tested on a similar dataset, the UNSW-NB15, it continues to demonstrate superior performance, indicating its strong generalizability.
- 21 February 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 144, 165-178
BEAST: Behavior as a Service for Trust management in IoT devices
- 21 February 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 144, 165-178
BEAST: Behavior as a Service for Trust management in IoT devices
- Open Access
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Beast: Behavior as a Service for Trust Management in Iot Devices
As the internet becomes intertwined into every aspect of human lives, security of the Internet of Things (IoT) becomes increasingly critical. IoT devices become the data source for variety of smart cities applications, where critical decisions are based on this collected data. If malicious actors control or tampered with the the data being transmitted, the integrity of an entire smart city will be compromised. Therefore, through monitoring the IoT devices’ behavior, anomalies can be detected and isolated to avoid any negative impact on decision making. This behavioral monitoring process will complement traditional trust management approaches, as more accurate trust value can be calculated without the need to rely on a majority consensus. In this work we present a behavior as a service methodology that implements a deep learning based behavioral model to accurately classify IoT devices’ interactions in the system. Through the Elo rating system, these classifications will be presented as a vector of behaviors per device, which dynamically reflects on the device’s trust in the system. This work presents an analysis of our methodology as well as a threat model. Using simulation, a real-world use-case is presented showing the interactions between IoT based devices. Our results show that our behavior as a service model is able to dynamically evaluate each IoT device’s trust as well as capture and mitigate multiple threats targeting the trust in the system.
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Open AccessBeast: Behavior as a Service for Trust Management in Iot Devices
As the internet becomes intertwined into every aspect of human lives, security of the Internet of Things (IoT) becomes increasingly critical. IoT devices become the data source for variety of smart cities applications, where critical decisions are based on this collected data. If malicious actors control or tampered with the the data being transmitted, the integrity of an entire smart city will be compromised. Therefore, through monitoring the IoT devices’ behavior, anomalies can be detected and isolated to avoid any negative impact on decision making. This behavioral monitoring process will complement traditional trust management approaches, as more accurate trust value can be calculated without the need to rely on a majority consensus. In this work we present a behavior as a service methodology that implements a deep learning based behavioral model to accurately classify IoT devices’ interactions in the system. Through the Elo rating system, these classifications will be presented as a vector of behaviors per device, which dynamically reflects on the device’s trust in the system. This work presents an analysis of our methodology as well as a threat model. Using simulation, a real-world use-case is presented showing the interactions between IoT based devices. Our results show that our behavior as a service model is able to dynamically evaluate each IoT device’s trust as well as capture and mitigate multiple threats targeting the trust in the system.