Imad Tareq
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Imad Tareq has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Salsabil Amin El-Regaily
Faculty of Computers and Information Sciences
3 shared publications Bassant M. Elbagoury
Faculty of Computer and Information Sciences, Ain Shams University, Cairo, Egypt
2 shared publications- El-Sayed M. El-Horbaty
Computer Science Department, Faculty of Computer and Information Sciences, Ain Shams University, Cairo, Egypt
2 shared publications - Bassant M. Elbagoury
Faculty of Computer and Information Sciences, Ain Shams University, Cairo 11566, Egypt
1 shared publication Bassant Mohamed Elbagoury
Faculty of Computer Science and Computer Engineering King Salman International Uni-versity. Faculty of Computer Science and information sciences Ain Shams University, Egypt
1 shared publication- Bassant Mohamed Elbagoury
Ain Shams University
1 shared publication
Latest Publications
- Open Access
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (4) , 4778-4794
Federated inception-multi-head attention models for cyber-attacks detection
With the proliferation of internet of things (IoT) devices, ensuring the security of these interconnected systems has become a critical concern. Cyberattacks targeting IoT devices pose significant threats to individuals and organizations due to the generation of vast amounts of data across many connected devices, which traditional centralized methods cannot solve. Federated learning (FL) could be a promising solution to mitigate privacy concerns associated with centralized approaches and address cybersecurity concerns. This paper uses FL and deep learning (DL) approaches to cybersecurity in IoT applications. The goal of cyber security is achieved by forming a federation of acquired and shared models at the head of the various participants. We use inception time and multi-head attention (CNN) algorithm based on FL to detect cyber-attacks and avoid data privacy leaks under two distribution modes, namely IID and Non-IID. In contrast, the FedAvg and FedMA algorithms aggregate local model updates. A global model is produced after several communication rounds between the IoT devices and the model parameter server. Cyber threats are simulated using edge-IIoT datasets. Experiment results show that the federated inception model's best global accuracy was 93, 91%, and 93, 49% using multi-head attention.
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (4) , 4778-4794
Open AccessFederated inception-multi-head attention models for cyber-attacks detection
With the proliferation of internet of things (IoT) devices, ensuring the security of these interconnected systems has become a critical concern. Cyberattacks targeting IoT devices pose significant threats to individuals and organizations due to the generation of vast amounts of data across many connected devices, which traditional centralized methods cannot solve. Federated learning (FL) could be a promising solution to mitigate privacy concerns associated with centralized approaches and address cybersecurity concerns. This paper uses FL and deep learning (DL) approaches to cybersecurity in IoT applications. The goal of cyber security is achieved by forming a federation of acquired and shared models at the head of the various participants. We use inception time and multi-head attention (CNN) algorithm based on FL to detect cyber-attacks and avoid data privacy leaks under two distribution modes, namely IID and Non-IID. In contrast, the FedAvg and FedMA algorithms aggregate local model updates. A global model is produced after several communication rounds between the IoT devices and the model parameter server. Cyber threats are simulated using edge-IIoT datasets. Experiment results show that the federated inception model's best global accuracy was 93, 91%, and 93, 49% using multi-head attention.
- Open Access
- 1 June 2024
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- Vol. 24 (2) , 18-27
MACHINE LEARNING FOR DETECTING INTERNET OF THINGS NETWORK CYBER-ATTACKS
With the proliferation of Internet of things devices, guaranteeing the security of these networked systems has become a top priority. Cyberattacks on IoT devices pose considerable risks toindividuals and companies because they generate massive amounts of sensitive data across numerous linked devices, making data privacy and integrity a key concern. Machine learning models can help classify different types of cyber-attacks in IoT networks based on logs of activities, analyze behaviors, and predict malicious or unusual activities. This research employs a parallel method utilizing Machine Learning techniques such as LDA, SVM, SVM+LDA, and QDA, on the WUSTL-IIOT database and compares it with traditional methods. The data is partitioned into smaller training datasets and trained in parallel. Experiments show that this parallel training system detects and forecasts cyber threats more accurately. The detection speed with the parallel ML models was high, and the best accuracy was 100% using the SVM+LDA model.
- 1 June 2024
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- Vol. 24 (2) , 18-27
Open AccessMACHINE LEARNING FOR DETECTING INTERNET OF THINGS NETWORK CYBER-ATTACKS
With the proliferation of Internet of things devices, guaranteeing the security of these networked systems has become a top priority. Cyberattacks on IoT devices pose considerable risks toindividuals and companies because they generate massive amounts of sensitive data across numerous linked devices, making data privacy and integrity a key concern. Machine learning models can help classify different types of cyber-attacks in IoT networks based on logs of activities, analyze behaviors, and predict malicious or unusual activities. This research employs a parallel method utilizing Machine Learning techniques such as LDA, SVM, SVM+LDA, and QDA, on the WUSTL-IIOT database and compares it with traditional methods. The data is partitioned into smaller training datasets and trained in parallel. Experiments show that this parallel training system detects and forecasts cyber threats more accurately. The detection speed with the parallel ML models was high, and the best accuracy was 100% using the SVM+LDA model.
- Open Access
- 15 March 2024
- Published by International Association of Online Engineering (IAOE) in International Journal of Online and Biomedical Engineering (iJOE)
- Vol. 20 (05) , 15-30
Deep Reinforcement Learning Approach for Cyberattack Detection
Recently, there has been a growing concern regarding the detrimental effects of cyberattacks on both infrastructure and users. Conventional safety measures, such as encryption, firewalls, and intrusion detection, are inadequate to safeguard cyber systems against emerging and evolving threats. To address this issue, researchers have turned to reinforcement learning (RL) as a potential solution for complex decision-making problems in cybersecurity. However, the application of RL faces various obstacles, including a lack of suitable training data, dynamic attack scenarios, and challenges in modeling real-world complexities. This paper suggests applying deep reinforcement learning (DRL), a deep framework, to simulate malicious cyberattacks and enhance cybersecurity. Our framework utilizes an agent-based model that is capable of continuous learning and adaptation within a dynamic network security environment. The agent determines the most optimal course of action based on the network’s state and the corresponding rewards received for its decisions. We present the outcomes of our experimentation with the application of DRL on a specific model, double deep Q-network (DDQN), utilizing policy gradient (PG) on three distinct datasets: NSL-KDD, CIC-IDS-2018, and AWID. Our research demonstrates that DRL can effectively improve cyberattack detection outcomes through our model and specific parameter adjustments.
- 15 March 2024
- Published by International Association of Online Engineering (IAOE) in International Journal of Online and Biomedical Engineering (iJOE)
- Vol. 20 (05) , 15-30
Open AccessDeep Reinforcement Learning Approach for Cyberattack Detection
Recently, there has been a growing concern regarding the detrimental effects of cyberattacks on both infrastructure and users. Conventional safety measures, such as encryption, firewalls, and intrusion detection, are inadequate to safeguard cyber systems against emerging and evolving threats. To address this issue, researchers have turned to reinforcement learning (RL) as a potential solution for complex decision-making problems in cybersecurity. However, the application of RL faces various obstacles, including a lack of suitable training data, dynamic attack scenarios, and challenges in modeling real-world complexities. This paper suggests applying deep reinforcement learning (DRL), a deep framework, to simulate malicious cyberattacks and enhance cybersecurity. Our framework utilizes an agent-based model that is capable of continuous learning and adaptation within a dynamic network security environment. The agent determines the most optimal course of action based on the network’s state and the corresponding rewards received for its decisions. We present the outcomes of our experimentation with the application of DRL on a specific model, double deep Q-network (DDQN), utilizing policy gradient (PG) on three distinct datasets: NSL-KDD, CIC-IDS-2018, and AWID. Our research demonstrates that DRL can effectively improve cyberattack detection outcomes through our model and specific parameter adjustments.
- Open Access
- 4 February 2024
- Published by International University of Sarajevo in Periodicals of Engineering and Natural Sciences (PEN)
- Vol. 12 (1) , 75-100
A survey about deep learning and federated Learning in cyberse-curity
Advances in Artificial Intelligence (AI) technology have led to the strengthening of traditional systems' cybersecurity capabilities in a variety of applications. However, these embedded machine learning models have exposed these systems to a new set of vulnerabilities known as AI assaults. These systems are now attractive targets for cyberattacks, jeopardizing the security and safety of bigger systems that include them. As a result, DL approaches are critical to transitioning network and system protection from providing safe communication between systems to intelligence systems in security. Federated learning (FL) is a new kind of AI based on heterogeneous datasets and decentralized training. FL is a unique research topic that is currently in its early phases. It has not yet gained wide acceptance in the community, owing mostly to privacy and security considerations. In this research, we first shed light on its privacy and security risks that must be discovered, analyzed, and recorded. FL is favored in scenarios where privacy and security are paramount issues. An extensive understanding of risk factors allows an FL adopter and implementer to construct a safe environment successfully while giving researchers a clear perspective of possible study domains. The survey in this paper intends to include an analysis of cybersecurity and DL approaches and modern advances to improve enhanced protection methods. It proposes a complete examination of FL's security and privacy issues to assist in bridging the gap between the current level of federated AI and a future in which broad adoption is achievable. We also propose a range of cybersecurity datasets and the most recently used rating standards.
- 4 February 2024
- Published by International University of Sarajevo in Periodicals of Engineering and Natural Sciences (PEN)
- Vol. 12 (1) , 75-100
Open AccessA survey about deep learning and federated Learning in cyberse-curity
Advances in Artificial Intelligence (AI) technology have led to the strengthening of traditional systems' cybersecurity capabilities in a variety of applications. However, these embedded machine learning models have exposed these systems to a new set of vulnerabilities known as AI assaults. These systems are now attractive targets for cyberattacks, jeopardizing the security and safety of bigger systems that include them. As a result, DL approaches are critical to transitioning network and system protection from providing safe communication between systems to intelligence systems in security. Federated learning (FL) is a new kind of AI based on heterogeneous datasets and decentralized training. FL is a unique research topic that is currently in its early phases. It has not yet gained wide acceptance in the community, owing mostly to privacy and security considerations. In this research, we first shed light on its privacy and security risks that must be discovered, analyzed, and recorded. FL is favored in scenarios where privacy and security are paramount issues. An extensive understanding of risk factors allows an FL adopter and implementer to construct a safe environment successfully while giving researchers a clear perspective of possible study domains. The survey in this paper intends to include an analysis of cybersecurity and DL approaches and modern advances to improve enhanced protection methods. It proposes a complete examination of FL's security and privacy issues to assist in bridging the gap between the current level of federated AI and a future in which broad adoption is achievable. We also propose a range of cybersecurity datasets and the most recently used rating standards.
- Top Cited PapersOpen Access
- 23 September 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (19) , 9572
Analysis of ToN-IoT, UNW-NB15, and Edge-IIoT Datasets Using DL in Cybersecurity for IoT
The IoT’s quick development has brought up several security problems and issues that cannot be solved using traditional intelligent systems. Deep learning (DL) in the field of artificial intelligence (AI) has proven to be efficient, with many advantages that can be used to address IoT cybersecurity concerns. This study trained two models of intelligent networks—namely, DenseNet and Inception Time—to detect cyber-attacks based on a multi-class classification method. We began our investigation by measuring the performance of these two networks using three datasets: the ToN-IoT dataset, which consists of heterogeneous data; the Edge-IIoT dataset; and the UNSW2015 dataset. Then, the results were compared by identifying several cyber-attacks. Extensive experiments were conducted on standard ToN-IoT datasets using the DenseNet multicategory classification model. The best result we obtained was an accuracy of 99.9% for Windows 10 with DenseNet, but by using the Inception Time approach we obtained the highest result for Windows 10 with the network, with 100% accuracy. As for using the Edge-IIoT dataset with the Inception Time approach, the best result was an accuracy of 94.94%. The attacks were also assessed in the UNSW-NB15 database using the Inception Time approach, which had an accuracy rate of 98.4%. Using window sequences for the sliding window approach and a six-window size to start training the Inception Time model yielded a slight improvement, with an accuracy rate of 98.6% in the multicategory classification.
- 23 September 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (19) , 9572
Top Cited PapersOpen AccessAnalysis of ToN-IoT, UNW-NB15, and Edge-IIoT Datasets Using DL in Cybersecurity for IoT
The IoT’s quick development has brought up several security problems and issues that cannot be solved using traditional intelligent systems. Deep learning (DL) in the field of artificial intelligence (AI) has proven to be efficient, with many advantages that can be used to address IoT cybersecurity concerns. This study trained two models of intelligent networks—namely, DenseNet and Inception Time—to detect cyber-attacks based on a multi-class classification method. We began our investigation by measuring the performance of these two networks using three datasets: the ToN-IoT dataset, which consists of heterogeneous data; the Edge-IIoT dataset; and the UNSW2015 dataset. Then, the results were compared by identifying several cyber-attacks. Extensive experiments were conducted on standard ToN-IoT datasets using the DenseNet multicategory classification model. The best result we obtained was an accuracy of 99.9% for Windows 10 with DenseNet, but by using the Inception Time approach we obtained the highest result for Windows 10 with the network, with 100% accuracy. As for using the Edge-IIoT dataset with the Inception Time approach, the best result was an accuracy of 94.94%. The attacks were also assessed in the UNSW-NB15 database using the Inception Time approach, which had an accuracy rate of 98.4%. Using window sequences for the sliding window approach and a six-window size to start training the Inception Time model yielded a slight improvement, with an accuracy rate of 98.6% in the multicategory classification.