A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile Systems
<p dir="ltr">Federated Learning (FL) is gaining traction in Android-based consumer electronics, enabling collaborative model training across decentralized devices while preserving data privacy. However, the increasing adoption of FL in these devices exposes them to adversarial attack...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1864513532059451392 |
|---|---|
| author | Faria Nawshin (21841598) |
| author2 | Devrim Unal (16864224) Mohammad Hammoudeh (7211567) Ponnuthurai N. Suganthan (17347024) |
| author2_role | author author author |
| author_facet | Faria Nawshin (21841598) Devrim Unal (16864224) Mohammad Hammoudeh (7211567) Ponnuthurai N. Suganthan (17347024) |
| author_role | author |
| dc.creator.none.fl_str_mv | Faria Nawshin (21841598) Devrim Unal (16864224) Mohammad Hammoudeh (7211567) Ponnuthurai N. Suganthan (17347024) |
| dc.date.none.fl_str_mv | 2025-11-07T09:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1109/tce.2025.3577905 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/A_Novel_Genetic_Algorithm_Optimized_Adversarial_Attack_in_Federated_Learning_for_Android-Based_Mobile_Systems/30542576 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Information and computing sciences Cybersecurity and privacy Machine learning Genetic algorithms adversarial attacks federated learning distributed systems benign android malware Perturbation methods Malware Consumer electronics Optimization Closed box Security Operating systems Data privacy Adaptation models |
| dc.title.none.fl_str_mv | A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile Systems |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">Federated Learning (FL) is gaining traction in Android-based consumer electronics, enabling collaborative model training across decentralized devices while preserving data privacy. However, the increasing adoption of FL in these devices exposes them to adversarial attacks that can compromise user data and device security. Given that Android applications are frequent targets for malware, ensuring the integrity of FL-based malware detection systems is critical. We introduce an attack framework that integrates Genetic Algorithms (GA) with two prominent adversarial techniques, namely, the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD), specifically designed for FL environments. Unlike traditional attacks that use fixed or heuristic perturbation parameters, our GA-driven method dynamically evolves perturbation parameters through multi-objective fitness optimization, producing highly adaptive and effective adversarial examples. The experimental results on the CICMalDroid 2020, KronoDroid, and AndroZoo Android malware detection datasets demonstrate a significant attack success rate, with a reduction of accuracy from 96–97% down to 24–29%, which surpasses the traditional FGSM and PGD variants. Similar results with GA-optimized PGD further validate our approach. Furthermore, our results demonstrate that existing defense mechanisms fail to adequately mitigate the impact of the proposed GA-optimized attacks.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Transactions on Consumer Electronics<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/tce.2025.3577905" target="_blank">https://dx.doi.org/10.1109/tce.2025.3577905</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_b73d5e25fc5b9b43ee0e76e9555e1f91 |
| identifier_str_mv | 10.1109/tce.2025.3577905 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/30542576 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile SystemsFaria Nawshin (21841598)Devrim Unal (16864224)Mohammad Hammoudeh (7211567)Ponnuthurai N. Suganthan (17347024)Information and computing sciencesCybersecurity and privacyMachine learningGenetic algorithmsadversarial attacksfederated learningdistributed systemsbenignandroid malwarePerturbation methodsMalwareConsumer electronicsOptimizationClosed boxSecurityOperating systemsData privacyAdaptation models<p dir="ltr">Federated Learning (FL) is gaining traction in Android-based consumer electronics, enabling collaborative model training across decentralized devices while preserving data privacy. However, the increasing adoption of FL in these devices exposes them to adversarial attacks that can compromise user data and device security. Given that Android applications are frequent targets for malware, ensuring the integrity of FL-based malware detection systems is critical. We introduce an attack framework that integrates Genetic Algorithms (GA) with two prominent adversarial techniques, namely, the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD), specifically designed for FL environments. Unlike traditional attacks that use fixed or heuristic perturbation parameters, our GA-driven method dynamically evolves perturbation parameters through multi-objective fitness optimization, producing highly adaptive and effective adversarial examples. The experimental results on the CICMalDroid 2020, KronoDroid, and AndroZoo Android malware detection datasets demonstrate a significant attack success rate, with a reduction of accuracy from 96–97% down to 24–29%, which surpasses the traditional FGSM and PGD variants. Similar results with GA-optimized PGD further validate our approach. Furthermore, our results demonstrate that existing defense mechanisms fail to adequately mitigate the impact of the proposed GA-optimized attacks.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Transactions on Consumer Electronics<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/tce.2025.3577905" target="_blank">https://dx.doi.org/10.1109/tce.2025.3577905</a></p>2025-11-07T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/tce.2025.3577905https://figshare.com/articles/journal_contribution/A_Novel_Genetic_Algorithm_Optimized_Adversarial_Attack_in_Federated_Learning_for_Android-Based_Mobile_Systems/30542576CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/305425762025-11-07T09:00:00Z |
| spellingShingle | A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile Systems Faria Nawshin (21841598) Information and computing sciences Cybersecurity and privacy Machine learning Genetic algorithms adversarial attacks federated learning distributed systems benign android malware Perturbation methods Malware Consumer electronics Optimization Closed box Security Operating systems Data privacy Adaptation models |
| status_str | publishedVersion |
| title | A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile Systems |
| title_full | A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile Systems |
| title_fullStr | A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile Systems |
| title_full_unstemmed | A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile Systems |
| title_short | A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile Systems |
| title_sort | A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile Systems |
| topic | Information and computing sciences Cybersecurity and privacy Machine learning Genetic algorithms adversarial attacks federated learning distributed systems benign android malware Perturbation methods Malware Consumer electronics Optimization Closed box Security Operating systems Data privacy Adaptation models |