HALOGrid—HyperAdaptive long short term memory model with intelligent grid optimization
<p>HALOGrid is an adaptive edge–cloud malware detection framework for IoT traffic. The approach couples a lightweight LSTM (residual paths, attention, drift-penalty regularization) for low-latency edge inference with a telemetry-driven tuner that performs real-time hyperparameter updates. The...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1864513521264361472 |
|---|---|
| author | Kamran Ahmad Awan (23643430) |
| author2 | Maha Abdelhaq (735574) Celestine Iwendi (18002485) Sonia Khan (23643433) Amina Salhi (23643436) Mueen Uddin (4903510) Raed Alsaqour (735575) |
| author2_role | author author author author author author |
| author_facet | Kamran Ahmad Awan (23643430) Maha Abdelhaq (735574) Celestine Iwendi (18002485) Sonia Khan (23643433) Amina Salhi (23643436) Mueen Uddin (4903510) Raed Alsaqour (735575) |
| author_role | author |
| dc.creator.none.fl_str_mv | Kamran Ahmad Awan (23643430) Maha Abdelhaq (735574) Celestine Iwendi (18002485) Sonia Khan (23643433) Amina Salhi (23643436) Mueen Uddin (4903510) Raed Alsaqour (735575) |
| dc.date.none.fl_str_mv | 2025-11-08T03:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1016/j.ijepes.2025.111327 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/HALOGrid_HyperAdaptive_long_short_term_memory_model_with_intelligent_grid_optimization/31890025 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Engineering Engineering practice and education Information and computing sciences Artificial intelligence Cybersecurity and privacy Distributed computing and systems software Machine learning Edge computing IoT malware detection Adaptive hyperparameter tuning Long Short-Term Memory Augmented grid search Real-time inference |
| dc.title.none.fl_str_mv | HALOGrid—HyperAdaptive long short term memory model with intelligent grid optimization |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p>HALOGrid is an adaptive edge–cloud malware detection framework for IoT traffic. The approach couples a lightweight LSTM (residual paths, attention, drift-penalty regularization) for low-latency edge inference with a telemetry-driven tuner that performs real-time hyperparameter updates. The tuner employs Augmented Grid Search (AGS): a stage-wise coarse-to-fine exploration with stochastic perturbations, early-stopping of inferior candidates, validation-weighted corrections, and expectation-weighted deployment. A resynchronization controller blends edge and cloud states using divergence- and delay-aware gating; updates are secured via mTLS transport and signed artifacts with rollback. The pipeline integrates preprocessing, drift estimation over multi-metric streams, adaptive learning-rate/regularization adjustment, and A/B deployment safety. Evaluation on CICIoT2023 reports 98.74% accuracy, 1.21% false positive rate, and 12.8,ms mean inference latency on Jetson Nano; energy consumption averages 52.5,mJ/inference. Compared with SGM, HPAI, DFN, ODMS, MIHT, AIMO, IEMS, and DOFD, HALOGrid maintains higher detection fidelity with lower tuning overhead through AGS and secure edge–cloud refinement.</p><h2>Other Information</h2> <p> Published in: International Journal of Electrical Power & Energy Systems<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.ijepes.2025.111327" target="_blank">https://dx.doi.org/10.1016/j.ijepes.2025.111327</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_564cfadb5fe185bc8ed308600450f29e |
| identifier_str_mv | 10.1016/j.ijepes.2025.111327 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/31890025 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | HALOGrid—HyperAdaptive long short term memory model with intelligent grid optimizationKamran Ahmad Awan (23643430)Maha Abdelhaq (735574)Celestine Iwendi (18002485)Sonia Khan (23643433)Amina Salhi (23643436)Mueen Uddin (4903510)Raed Alsaqour (735575)EngineeringEngineering practice and educationInformation and computing sciencesArtificial intelligenceCybersecurity and privacyDistributed computing and systems softwareMachine learningEdge computingIoT malware detectionAdaptive hyperparameter tuningLong Short-Term MemoryAugmented grid searchReal-time inference<p>HALOGrid is an adaptive edge–cloud malware detection framework for IoT traffic. The approach couples a lightweight LSTM (residual paths, attention, drift-penalty regularization) for low-latency edge inference with a telemetry-driven tuner that performs real-time hyperparameter updates. The tuner employs Augmented Grid Search (AGS): a stage-wise coarse-to-fine exploration with stochastic perturbations, early-stopping of inferior candidates, validation-weighted corrections, and expectation-weighted deployment. A resynchronization controller blends edge and cloud states using divergence- and delay-aware gating; updates are secured via mTLS transport and signed artifacts with rollback. The pipeline integrates preprocessing, drift estimation over multi-metric streams, adaptive learning-rate/regularization adjustment, and A/B deployment safety. Evaluation on CICIoT2023 reports 98.74% accuracy, 1.21% false positive rate, and 12.8,ms mean inference latency on Jetson Nano; energy consumption averages 52.5,mJ/inference. Compared with SGM, HPAI, DFN, ODMS, MIHT, AIMO, IEMS, and DOFD, HALOGrid maintains higher detection fidelity with lower tuning overhead through AGS and secure edge–cloud refinement.</p><h2>Other Information</h2> <p> Published in: International Journal of Electrical Power & Energy Systems<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.ijepes.2025.111327" target="_blank">https://dx.doi.org/10.1016/j.ijepes.2025.111327</a></p>2025-11-08T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.ijepes.2025.111327https://figshare.com/articles/journal_contribution/HALOGrid_HyperAdaptive_long_short_term_memory_model_with_intelligent_grid_optimization/31890025CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/318900252025-11-08T03:00:00Z |
| spellingShingle | HALOGrid—HyperAdaptive long short term memory model with intelligent grid optimization Kamran Ahmad Awan (23643430) Engineering Engineering practice and education Information and computing sciences Artificial intelligence Cybersecurity and privacy Distributed computing and systems software Machine learning Edge computing IoT malware detection Adaptive hyperparameter tuning Long Short-Term Memory Augmented grid search Real-time inference |
| status_str | publishedVersion |
| title | HALOGrid—HyperAdaptive long short term memory model with intelligent grid optimization |
| title_full | HALOGrid—HyperAdaptive long short term memory model with intelligent grid optimization |
| title_fullStr | HALOGrid—HyperAdaptive long short term memory model with intelligent grid optimization |
| title_full_unstemmed | HALOGrid—HyperAdaptive long short term memory model with intelligent grid optimization |
| title_short | HALOGrid—HyperAdaptive long short term memory model with intelligent grid optimization |
| title_sort | HALOGrid—HyperAdaptive long short term memory model with intelligent grid optimization |
| topic | Engineering Engineering practice and education Information and computing sciences Artificial intelligence Cybersecurity and privacy Distributed computing and systems software Machine learning Edge computing IoT malware detection Adaptive hyperparameter tuning Long Short-Term Memory Augmented grid search Real-time inference |