Heba Ismail
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
Heba Ismail has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- Ashraf Khalil
College of Technological Innovation, Zayed University, Abu Dhabi, UAE
5 shared publications Boumediene Belkhouche
College of Information Technology, United Arab Emirates University, Al Ain, United Arab Emirates
5 shared publications- Saad Harous
Department of Computer science, University of Sharjah, Sharjah, United Arab Emirates
5 shared publications Saad Harous
Professor, College of Computing and Informatics, University of Sharjah
4 shared publications- Alramzana Nujum Navaz
Department of Computer Science and Software Engineering, College of Information Technology, UAE University, Al Ain P.O. Box 15551, United Arab Emirates
3 shared publications - Mohamed Adel Serhani
University of Sharjah
3 shared publications
Latest Publications
- Open Access
- 23 October 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1) , 1596
Paired response final divergence signatures of jailbreak vulnerability in large language models
- 23 October 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1) , 1596
Open AccessPaired response final divergence signatures of jailbreak vulnerability in large language models
- Open Access
- 20 August 2026
- Published by MDPI AG in Information
- Vol. 17 (8) , 803
SEM-PDPL: Semantic Exposure Graphs for Privacy-Law-Informed Risk Assessment of Public Social-Media Data
Public social-media content often contains self-disclosed personal attributes that appear low-risk in isolation but become privacy-relevant when linked across posts, platform accounts, or user-level traces. Existing research has advanced privacy-sensitive content detection, de-anonymization analysis, social-media research ethics, and privacy-compliance workflows; however, limited work operationalizes how personal-data disclosures combine structurally and how these structures can be translated into auditable governance actions. This paper proposes SEM-PDPL, a computational, privacy-law-informed risk-assessment framework for modeling public social-media exposure as semantic exposure graphs and mapping graph patterns to controls aligned with the United Arab Emirates Personal Data Protection Law (PDPL) and compatible with GDPR principles. SEM-PDPL combines governance scoping; a PDPL-informed disclosure taxonomy; hybrid extraction using rule-based methods; named-entity recognition; fine-tuned BERT; and schema-constrained large language model annotation, followed by graph construction at post, platform, corpus, and persona levels. The framework is evaluated on a synthetic multi-platform corpus of 1095 posts generated for 150 personas across 290 platform accounts. Results show that, within this controlled synthetic corpus, fine-tuned BERT provides the strongest extraction performance among six evaluated methods, achieving a macro-F1 of 0.975. Graph analysis shows that exposure density increases with aggregation, rising from 0.275 at post level to 1.000 at corpus level, and from 0.859 at platform level to 0.967 at persona level. Across all graph resolutions, quasi-identifiers emerge as the dominant weighted-degree and betweenness node, indicating that ordinary location, employer, school, and demographic cues often function as bridges connecting sensitive categories such as health and biometric data to identifying information. These findings indicate that, within this controlled corpus, privacy risk in public social-media data is not only attribute-based but also structurally graph-shaped. SEM-PDPL contributes an explainable and reproducible framework for identifying exposure hubs, sensitive bridges, and aggregation risks before applying masking, minimization, exclusion, retention, or review controls. The framework does not automate legal compliance; rather, it provides evidence-based decision support for privacy-aware social-media analytics.
- 20 August 2026
- Published by MDPI AG in Information
- Vol. 17 (8) , 803
Open AccessSEM-PDPL: Semantic Exposure Graphs for Privacy-Law-Informed Risk Assessment of Public Social-Media Data
Public social-media content often contains self-disclosed personal attributes that appear low-risk in isolation but become privacy-relevant when linked across posts, platform accounts, or user-level traces. Existing research has advanced privacy-sensitive content detection, de-anonymization analysis, social-media research ethics, and privacy-compliance workflows; however, limited work operationalizes how personal-data disclosures combine structurally and how these structures can be translated into auditable governance actions. This paper proposes SEM-PDPL, a computational, privacy-law-informed risk-assessment framework for modeling public social-media exposure as semantic exposure graphs and mapping graph patterns to controls aligned with the United Arab Emirates Personal Data Protection Law (PDPL) and compatible with GDPR principles. SEM-PDPL combines governance scoping; a PDPL-informed disclosure taxonomy; hybrid extraction using rule-based methods; named-entity recognition; fine-tuned BERT; and schema-constrained large language model annotation, followed by graph construction at post, platform, corpus, and persona levels. The framework is evaluated on a synthetic multi-platform corpus of 1095 posts generated for 150 personas across 290 platform accounts. Results show that, within this controlled synthetic corpus, fine-tuned BERT provides the strongest extraction performance among six evaluated methods, achieving a macro-F1 of 0.975. Graph analysis shows that exposure density increases with aggregation, rising from 0.275 at post level to 1.000 at corpus level, and from 0.859 at platform level to 0.967 at persona level. Across all graph resolutions, quasi-identifiers emerge as the dominant weighted-degree and betweenness node, indicating that ordinary location, employer, school, and demographic cues often function as bridges connecting sensitive categories such as health and biometric data to identifying information. These findings indicate that, within this controlled corpus, privacy risk in public social-media data is not only attribute-based but also structurally graph-shaped. SEM-PDPL contributes an explainable and reproducible framework for identifying exposure hubs, sensitive bridges, and aggregation risks before applying masking, minimization, exclusion, retention, or review controls. The framework does not automate legal compliance; rather, it provides evidence-based decision support for privacy-aware social-media analytics.
- 2 August 2026
- Published by Springer Nature
- p. 173-184
AI for Sustainable Health in Smart Cities: An Empirical Study
- 2 August 2026
- Published by Springer Nature
- p. 173-184
AI for Sustainable Health in Smart Cities: An Empirical Study
- 2 August 2026
- Published by Springer Nature
- p. 160-172
Fraud Detection in the Open Metaverse: Machine Learning Approaches for Secure Connected Communities
- 2 August 2026
- Published by Springer Nature
- p. 160-172
Fraud Detection in the Open Metaverse: Machine Learning Approaches for Secure Connected Communities
- Open Access
- 20 February 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1)
Image and metadata-driven personality inference for career recommendation: a social media-based AI framework for adolescents
- 20 February 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1)
Open AccessImage and metadata-driven personality inference for career recommendation: a social media-based AI framework for adolescents
- 2 January 2026
- Published by Springer Nature
- p. 429-440
Leveraging VR and Fine-Tuned Language Models for UAE Dialect Interview Training: The TQDR Case Study
- 2 January 2026
- Published by Springer Nature
- p. 429-440
Leveraging VR and Fine-Tuned Language Models for UAE Dialect Interview Training: The TQDR Case Study
- 20 November 2025
- Published by Springer Nature
- p. 629-642
Enhancing Clear-Cell Renal Cell Carcinoma Survival Prediction Using Explainable Machine Learning
- 20 November 2025
- Published by Springer Nature
- p. 629-642
Enhancing Clear-Cell Renal Cell Carcinoma Survival Prediction Using Explainable Machine Learning
- 1 October 2025
- Published by Springer Nature
- p. 529-547
Adversarial Attacks on Large Language Models: A Survey
- 1 October 2025
- Published by Springer Nature
- p. 529-547
Adversarial Attacks on Large Language Models: A Survey
- 1 October 2025
- Published by Springer Nature
- p. 561-573
Leveraging Large Language Models for Misinformation Detection: A Focus on Public Health Misinformation on Social Media
- 1 October 2025
- Published by Springer Nature
- p. 561-573
Leveraging Large Language Models for Misinformation Detection: A Focus on Public Health Misinformation on Social Media
- Open Access
- 19 February 2025
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 20 (5) , 4489-4500
Enhancing online toxicity detection on gaming networks: a novel embeddings-based valence lexicon approach
- 19 February 2025
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 20 (5) , 4489-4500
Open AccessEnhancing online toxicity detection on gaming networks: a novel embeddings-based valence lexicon approach