Mohamed Ebrahim Torky

Dr. Mohamed Ebrahim Torky

Higher Institute of Computer Science and Information Systems- Culture & Science City, Giza, Al Jīzah, Egypt
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2019 in International Journal of Advanced Computer Science and Applications
Verified
Journal Article
Open access
PDF file
MTMohamed Ebrahim Torky
Mohamed Ebrahim Torky
Emad NabilEmad Nabil
Emad Nabil
WMwael said abdelmageed Mohamed
wael said abdelmageed Mohamed
Rumors and misleading information detection and prevention still represent a big challenge against social network developers and researchers. Since newsworthy information propagation is a traditional behavior of most of the users in social media, then verifying information credibility and reliability is indeed a vital security requirement for social network platforms. Due to its immutability, security, tamper-proof and P2P design, Blockchain as a powerful technology can provide a magical solution to overcome this challenge. This Paper introduces a novel blockchain approach called Proof of Credibility (PoC) for detecting fake news and blocking its propagation in social networks. The functionality of the PoC protocol has been simulated on two datasets of newsworthy tweets collected from different news sources on Twitter. The results clarified a satisfying performance and efficiency of the proposed approach in detecting rumors and blocking its propagation.

2 April 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Open access
Tarek GaberTarek Gaber
Tarek Gaber
TATarek Ali
Tarek Ali
MNMathew Nicho
Mathew Nicho
MTMohamed Ebrahim Torky
Mohamed Ebrahim Torky
The Internet of Flying Things (IoFT) holds significant promise in fields like disaster management and surveillance. However, it is increasingly vulnerable to cyberattacks that can compromise the confidentiality, integrity, and availability (CIA) of sensitive data. Despite the growing interest in proposing intrusion detection systems (IDSs) for IoFT networks, current literature faces key limitations, particularly the shortage of publicly available IoFT datasets with diverse attacks, and the fact that existing IDSs lack robustness against sophisticated adversarial machine learning (ML) attacks. This article is the first study to address these limitations by proposing a more resilient and accurate IDS tailored for IoFT networks (RIDS-IoFT). We introduce a novel IDS that leverages generative adversarial networks (GANs) to generate a hybrid dataset that combines real IoFT traffic data with GAN-generated adversarial attacks, addressing the dataset diversity issue. Additionally, we introduce an innovative adversarial training method to enhance the system’s defense against evolving threats, such as fast gradient sign method (FGSM), basic iterative method (BIM), and Carlini & Wagner (C&W) attacks. The proposed RIDS-IoFT was evaluated using four ML models, random forest (RF), decision tree (DT), support vector machine (SVM), and logistic regression (LR), on two datasets: 1) ECU-IoFT and 2) CICIDS2018. The IDS’s performance was assessed based on its ability to detect both traditional and adversarial attacks. The results show that the RF model achieved the highest detection accuracy, up to 96.5%, demonstrating superior performance across both real and hybrid datasets. The proposed RIDS-IoFT not only enhances detection accuracy but also strengthens resilience against adversarial threats, making it suitable for resource-constrained IoFT environments. In conclusion, this study presents a comprehensive approach to securing IoFT networks by combining real and synthetic data, improving IDS robustness and accuracy against both traditional and adversarial attacks.

14 March 2023 in Applied Soft Computing
Verified
Journal Article
Closed access
MTMohamed Ebrahim Torky
Mohamed Ebrahim Torky
GDGhada Dahy
Ghada Dahy
Abou ELLa HassanienAbou ELLa Hassanien
Abou ELLa Hassanien

5 April 2023 in International Journal of Computational Intelligence Systems
Verified
Journal Article
Open access
PDF file
MTMohamed Ebrahim Torky
Mohamed Ebrahim Torky
IGIbrahim Gad
Ibrahim Gad
Abou ELLa HassanienAbou ELLa Hassanien
Abou ELLa Hassanien
Utilizing Artificial Intelligence (AI) techniques to forecast, recognize, and classify financial crisis roots are important research challenges that have attracted the interest of researchers. Moreover, the Explainable Artificial Intelligence (XAI) concept enables AI techniques to interpret the results of processing and testing complex data patterns so that humans can find efficient ways to infer and interpret the logic behind classifying complex data patterns. This paper proposes a novel XAI model to automatically recognize financial crisis roots and interprets the features selection operation. Using a benchmark dataset, the proposed XAI model utilized the pigeon optimizer to optimize the feature selection operation, and then the Gradient Boosting classifier is utilized to recognize financial crisis roots based on the obtained reduct of the most important features. The practical results showed that the short-term interest rates feature is the most important feature by which financial crisis roots can be detected. Moreover, the classification results showed that the built-in Gradient Boosting classifier in the Pigeon Inspired Optimizer (PIO) algorithm achieved training and testing accuracy of 99% and 96.7%, respectively, in recognizing financial crisis roots, which is an efficient and better performance compared to the random forest classifier.

4 September 2022 in Drones
Verified
Journal Article
Open access
PDF file
MTMohamed Ebrahim Torky
Mohamed Ebrahim Torky
MEMohamed Eldosuky
Mohamed Eldosuky
EGEssam Goda
Essam Goda
TVTomas Vantuch
Tomas Vantuch
Abou ELLa HassanienAbou ELLa Hassanien
Abou ELLa Hassanien
Unmanned aerial vehicles (UAVs) have emerged as a powerful technology for introducing untraditional solutions to many challenges in non-military fields and industrial applications in the next few years. However, the limitations of a drone’s battery and the available optimal charging techniques represent a significant challenge in using UAVs on a large scale. This problem means UAVs are unable to fly for a long time; hence, drones’ services fail dramatically. Due to this challenge, optimizing the scheduling of drone charging may be an unusual solution to drones’ battery problems. Moreover, authenticating drones and verifying their charging transactions with charging stations is an essential associated problem. This paper proposes a scheduling and secure drone charging system in response to these challenges. The proposed system was simulated on a generated dataset consisting of 300 drones and 50 charging station points to evaluate its performance. The optimization of the proposed scheduling methodology was based on the particle swarm optimization (PSO) algorithm and game theory-based auction model. In addition, authenticating and verifying drone charging transactions were executed using a proposed blockchain protocol. The optimization and scheduling results showed the PSO algorithm’s efficiency in optimizing drone routes and preventing drone collisions during charging flights with low error rates with an MAE = 0.0017 and an MSE = 0.0159. Moreover, the investigation to authenticate and verify the drone charging transactions showed the efficiency of the proposed blockchain protocol while simulating the proposed system on the Ethereum platform. The obtained results clarified the efficiency of the proposed blockchain protocol in executing drone charging transactions within a short time and low latency within an average of 0.34 s based on blockchain performance metrics. Moreover, the proposed scheduling methodology achieved a 96.8% success rate of drone charging cases, while only 3.2% of drones failed to charge after three scheduling rounds.

8 January 2017 in International Journal of Computer Network and Information Security
Verified
Journal Article
Open access
PDF file
AMAli M. Meligy
Ali M. Meligy
HIHani M. Ibrahim
Hani M. Ibrahim
MTMohamed Ebrahim Torky
Mohamed Ebrahim Torky
Impersonating users' identity in Online Social Networks (OSNs) is one of the open dilemmas from security and privacy point of view. Scammers and adversaries seek to create set of fake profiles to carry out malicious behaviors and online social crimes in social media. Recognizing the identity of Fake Profiles is an urgent issue of concern to the attention of researchers. In this paper, we propose a detection technique called Fake Profile Recognizer (FPR) for verifying the identity of profiles, and detecting the fake profiles in OSNs. The detection method in our proposed technique is based on utilizing Regular Expression (RE) and Deterministic Finite Automaton (DFA) approaches. We evaluated our proposed detection technique on three datasets types of OSNs: Facebook, Google+, and Twitter. The results explored high Precision, Recall, accuracy, and low False Positive Rates (FPR) of detecting Fake Profiles in the three datasets.