Mohammed Salem Atoum

Dr. Mohammed Salem Atoum

Department of Computer Science, The University of Jordan, Amman, Al ‘Āşimah, Jordan
Department of Computer Science, The University of Jordan, Am...

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
6 October 2025 in Engineering, Technology & Applied Science Research
Verified
Journal Article
Open access
PDF file
MAMohammad Alnabhan
Mohammad Alnabhan
AEAli El-Qasass
Ali El-Qasass
Mohammed Salem AtoumMohammed Salem Atoum
Mohammed Salem Atoum
Qasem Abu Al-HaijaQasem Abu Al-Haija
Qasem Abu Al-Haija
AHAhmad khader Habboush
Ahmad khader Habboush
Protecting the confidentiality of images is considered critical for all industries. Encryption stands out as the foremost protective strategy for image security. However, various image dimensions and quality concerns challenge conventional encryption methods in balancing the security objective, substantial computational resources, and image quality. This paper presents a lightweight cryptographic approach designed to match the robustness of traditional encryption schemes while minimizing the computational and time requirements to be more suitable for real-time applications and IoT environments. The proposed approach extracts the three Most Significant Bit (MSB) planes from the original image. Then, it applies a permutation on each bit plane using a chaotic logistic map to generate the key used as new indices for effective permutation of pixel locations. A set of performance metrics, such as the Correlation Coefficient (CC), Mean Square Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and CPU and RAM utilization, is used in the evaluation process. The results indicate that the proposed approach outperforms the traditional Advanced Encryption Standard (AES) in terms of computational efficiency and overhead. A 2% reduction in CPU and RAM utilization and a 96% decrease in extraction time were achieved while maintaining comparable security based on MSE, PSNR, and CC to AES. This improvement in efficiency is achieved while maintaining an acceptable level of security, which makes it more suitable for resource-constrained IoT devices.

21 April 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
Mohammed Salem AtoumMohammed Salem Atoum
Mohammed Salem Atoum
ALAA ALAROODALAA ALAROOD
ALAA ALAROOD
EAEesa Alsolami
Eesa Alsolami
AIAdamu Abubakar Ibrahim
Adamu Abubakar Ibrahim
AHAhmad K. Al Hwaitat
Ahmad K. Al Hwaitat
Izzat AlsmadiIzzat Alsmadi
Izzat Alsmadi
This study examines multi-lexical data sources, utilizing an extracted dataset from an open-source corpus and the Global Terrorism Datasets (GTDs), to predict lexical patterns that are directly linked to terrorism. This is essential as specific patterns within a textual context can facilitate the identification of terrorism-related content. The research methodology focuses on generating a corpus from various published works and extracting texts pertinent to “terrorism”. Afterwards, we extract additional lexical contexts of GTDs that directly relate to terrorism. The integration of multi-lexical data sources generates lexical patterns linked to terrorism. Machine learning models were used to train the dataset. We conducted two primary experiments and analyzed the results. The analysis of data obtained from open sources reveals that while the Extra Trees model achieved the highest accuracy at 94.31%, the XGBoost model demonstrated superior overall performance with a higher recall (81.32%) and F1-Score (83.06%) after tuning, indicating a better balance between sensitivity and precision. Similarly, on the GTD dataset, XGBoost consistently outperformed other models in recall and the F1-score, making it a more suitable candidate for tasks where minimizing false negatives is critical. This implies that we can establish a specific co-occurrence and context within the terrorism dataset from multiple lexical data sources in effectively identifying certain multi-lexical patterns such as “Suicide Attack/Casualty”, “Civilians/Victims”, and “Hostage Taking/Abduction” across various applications or contexts. This will facilitate the development of a framework for understanding the lexical patterns associated with terrorism.

15 October 2025 in Cluster Computing
Verified
Journal Article
Open access
PDF file
ALAA ALAROODALAA ALAROOD
ALAA ALAROOD
Mohammed Salem AtoumMohammed Salem Atoum
Mohammed Salem Atoum
AMAzizah Abdul Manaf
Azizah Abdul Manaf
AIAdamu Abubakar Ibrahim
Adamu Abubakar Ibrahim
Izzat AlsmadiIzzat Alsmadi
Izzat Alsmadi
Obstacle detection remains vital in autonomous navigation and assistive technologies, especially for visually impaired individuals. This work introduces an enhanced obstacle detection framework based on a Bilateral Vision Transformer and Convolution Kernel Neural Network (BViT-CKNN). The system incorporates stereo vision data and applies a bilateral filter to reduce noise while preserving edge details. A Vision Transformer (ViT) model is then used for global feature extraction, and a Convolution Kernel Neural Network (CKNN) captures fine-grained local features. Evaluated using the COCO dataset, the proposed BViT-CKNN achieves superior performance in precision (0.93), recall (0.91), F1-score (0.92), and Mean Absolute Error (MAE) reduction (3.16%) compared to existing methods.

1 November 2024 in Journal of Information Systems Education
Verified
Journal Article
Open access
PDF file
MAMuhammad Al-Abdullah
Muhammad Al-Abdullah
AYAlper Yayla
Alper Yayla
Mohammed Salem AtoumMohammed Salem Atoum
Mohammed Salem Atoum
In today’s cybersecurity landscape, organizations need frameworks that provide a holistic approach to risk assessment as part of the risk management process. This case introduces SecureEnd Solutions, a rapidly growing cybersecurity company, and its core team, including Alan Touring, Ada Lovecode, Bob Jobs, and Suzan, the head of development. The company must conduct a detailed risk assessment to obtain ISO/IEC 27001 certification using a combination of ISO/IEC 27005:2022 and NIST SP 800-30 guidelines. Students will engage with the characters and the company’s technological ecosystem to apply risk assessment standards, enhancing their decision-making, analytical, and problem-solving skills in a real-world scenario.

26 August 2023 in Cluster Computing
Verified
Journal Article
Closed access
PDF file
GLGongbo Liang
Gongbo Liang
Mohammed Salem AtoumMohammed Salem Atoum
Mohammed Salem Atoum
XXXin Xing
Xin Xing
Izzat AlsmadiIzzat Alsmadi
Izzat Alsmadi

12 June 2025 in Research Square
Verified
Preprint
Open access
PDF file
ALAA ALAROODALAA ALAROOD
ALAA ALAROOD
Mohammed Salem AtoumMohammed Salem Atoum
Mohammed Salem Atoum
AMAzizah Abdul Manaf
Azizah Abdul Manaf
AIAdamu Abubakar Ibrahim
Adamu Abubakar Ibrahim
Izzat AlsmadiIzzat Alsmadi
Izzat Alsmadi
Obstacle detection remains vital in autonomous navigation and assistive technologies, especially for visually impaired individuals. This work introduces an enhanced obstacle detection framework based on a Bilateral Vision Transformer and Convolution Kernel Neural Network (BViT-CKNN). The system incorporates stereo vision data and applies a bilateral filter to reduce noise while preserving edge details. A Vision Transformer (ViT) model is then used for global feature extraction, and a Convolution Kernel Neural Network (CKNN) captures fine-grained local features. Evaluated using the COCO dataset, the proposed BViT-CKNN achieves superior performance in precision (0.93), recall (0.91), F1-score (0.92), and Mean Absolute Error (MAE) reduction (3.16%) compared to existing methods.