Inbithaq Ahmed Shakir
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Inbithaq Ahmed Shakir has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Amjed Abbas Ahmed
Faculty of Information Science and Technology, University Kebangsaan Malaysia, Bangi 43600, Malaysia
2 shared publications Abubakar Amoo Akinlawon
Department of Electrical Engineering, Aliko Dangote University of Science and Technology, Wudil 713101, Kano, Nigeria
1 shared publication- Aladdin Al Zahran
Sohar University
1 shared publication - Hamood Mohammed AlRumhi
Sultan Qaboos University
1 shared publication - Haneen Siraj Ibrahim
Department of Computer Science, Mustansiriyah University, Baghdad, Iraq
1 shared publication - Mohammad Ahmed Alomari
Universiti Teknikal Malaysia Melaka
1 shared publication
Latest Publications
- Open Access
- 27 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 25 (11) , 1-25
TRIDENT-SE: Translation-Divergence and Intent Graph Learning for Cross-Lingual Phishing and Social Engineering Detection in Arabic–English Communication
In multilingual communication, dialectal differences, code-switching, and culturally influenced persuasive approaches make phishing and social engineering attacks more widespread, testing existing detection technologies. Traditional monolingual and multilingual transformer-based methods concentrate on lexical and semantic similarities and are less resistant to paraphrase or translation-induced semantic changes. TRIDENT-SE (Translation-Divergence and Intent Graph-based Detection of Social Engineering) is a hybrid cross-lingual cyber threat detection system that uses massive language models and graph-based behavioral reasoning. An instruction-tuned Large Language Model contextualizes English, Modern Standard Arabic, regional Arabic dialects, and romanized Arabic phrases. TDE modules assess semantic differences between original and translated messages, enhancing translation noise and language change resilience. An Intent–Action Graph Reasoning (IAGR) module simulates attacker strategies by correlating urgency, impersonation, credential solicitation, authority exploitation, and money demands. TRIDENT-SE increases F1-score by 9.4% over monolingual baselines and 5.1% over state-of-the-art multilingual transformer models in code-switching, dialect-shift, and adversarial paraphrase situations on an annotated Arabic–English dataset. Arabic-speaking human-centered evaluation participants had 18.7% more correct risk assessments and 22.3% less harmful user responses. Multilingual phishing and social engineering detection is robust and interpretable using translation-aware semantic analysis and intent-driven graph learning.
- 27 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 25 (11) , 1-25
Open AccessTRIDENT-SE: Translation-Divergence and Intent Graph Learning for Cross-Lingual Phishing and Social Engineering Detection in Arabic–English Communication
In multilingual communication, dialectal differences, code-switching, and culturally influenced persuasive approaches make phishing and social engineering attacks more widespread, testing existing detection technologies. Traditional monolingual and multilingual transformer-based methods concentrate on lexical and semantic similarities and are less resistant to paraphrase or translation-induced semantic changes. TRIDENT-SE (Translation-Divergence and Intent Graph-based Detection of Social Engineering) is a hybrid cross-lingual cyber threat detection system that uses massive language models and graph-based behavioral reasoning. An instruction-tuned Large Language Model contextualizes English, Modern Standard Arabic, regional Arabic dialects, and romanized Arabic phrases. TDE modules assess semantic differences between original and translated messages, enhancing translation noise and language change resilience. An Intent–Action Graph Reasoning (IAGR) module simulates attacker strategies by correlating urgency, impersonation, credential solicitation, authority exploitation, and money demands. TRIDENT-SE increases F1-score by 9.4% over monolingual baselines and 5.1% over state-of-the-art multilingual transformer models in code-switching, dialect-shift, and adversarial paraphrase situations on an annotated Arabic–English dataset. Arabic-speaking human-centered evaluation participants had 18.7% more correct risk assessments and 22.3% less harmful user responses. Multilingual phishing and social engineering detection is robust and interpretable using translation-aware semantic analysis and intent-driven graph learning.
- Open Access
- 30 June 2025
- Published by Nabea Al-Ajyal Foundation press in CyberSystem Journal
- Vol. 2 (1) , 1-9
The Role of Deep Learning in Enhancing Solar Panel Efficiency: A Review of Models and Metrics
The rising desire to get long-term power has stepped up the utilisation of solar photovoltaic (PV) systems all over the world. Nonetheless, keeping the solar panels in optimal performance is a major concern because of the changeable environmental conditions, wear and tear of the equipment and breakdown of operations. Deep learning (DL) has become an efficient solution of offering sophistication in predicting solar power generation, fault detection, and optimization of the performance. The review will go in depth over several DL methodologies, such as, CNN, LSTM, Transformer-based models, Reinforcement Learning, GANs, and hybrid architectures of CNN-LSTM. The implementation of each model, performance metrics of MAE, RMSE, R2, and MAPE as well as weak points and advantages of each model, are provided in their relation to increasing PV efficiency. Moreover, the paper covers real-life data, real-life implementations, and comparative performance of these models in addressing critical issues in the solar energy systems. Nonetheless, despite the significant progress, there are still a number of challenges that need to be addressed, among which are the data sparsity, inability to generalize the models to different areas of interest, computational limitations, and inability to interpret the models. To resolve these problems, future directions outlined by the present paper include the creation of lightweight models of edge-AI, the use of transfer learning to achieve regional adaptability, the possibility of Explainable AI (XAI), and the combination of deep learning and IoT and digital twin technology. I would say that the given comprehensive review is an excellent source of information that can be used by researchers, engineers, and policymakers who want to use deep learning to make solar panels as efficient as possible to deliver more resilient, reliable, and sustainable energy delivery.
- 30 June 2025
- Published by Nabea Al-Ajyal Foundation press in CyberSystem Journal
- Vol. 2 (1) , 1-9
Open AccessThe Role of Deep Learning in Enhancing Solar Panel Efficiency: A Review of Models and Metrics
The rising desire to get long-term power has stepped up the utilisation of solar photovoltaic (PV) systems all over the world. Nonetheless, keeping the solar panels in optimal performance is a major concern because of the changeable environmental conditions, wear and tear of the equipment and breakdown of operations. Deep learning (DL) has become an efficient solution of offering sophistication in predicting solar power generation, fault detection, and optimization of the performance. The review will go in depth over several DL methodologies, such as, CNN, LSTM, Transformer-based models, Reinforcement Learning, GANs, and hybrid architectures of CNN-LSTM. The implementation of each model, performance metrics of MAE, RMSE, R2, and MAPE as well as weak points and advantages of each model, are provided in their relation to increasing PV efficiency. Moreover, the paper covers real-life data, real-life implementations, and comparative performance of these models in addressing critical issues in the solar energy systems. Nonetheless, despite the significant progress, there are still a number of challenges that need to be addressed, among which are the data sparsity, inability to generalize the models to different areas of interest, computational limitations, and inability to interpret the models. To resolve these problems, future directions outlined by the present paper include the creation of lightweight models of edge-AI, the use of transfer learning to achieve regional adaptability, the possibility of Explainable AI (XAI), and the combination of deep learning and IoT and digital twin technology. I would say that the given comprehensive review is an excellent source of information that can be used by researchers, engineers, and policymakers who want to use deep learning to make solar panels as efficient as possible to deliver more resilient, reliable, and sustainable energy delivery.