Federated Learning for Cybersecurity: A Privacy-Preserving Approach
The growing number of cyber threats and the implementation of stringent privacy regulations have revealed significant shortcomings in traditional centralized machine learning models, especially in distributed systems like the Internet of Things (IoT). This study presents a Federated Learning (FL) fr...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/12/6878 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839654853905743872 |
|---|---|
| author | Edi Marian Timofte Mihai Dimian Adrian Graur Alin Dan Potorac Doru Balan Ionut Croitoru Daniel-Florin Hrițcan Marcel Pușcașu |
| author_facet | Edi Marian Timofte Mihai Dimian Adrian Graur Alin Dan Potorac Doru Balan Ionut Croitoru Daniel-Florin Hrițcan Marcel Pușcașu |
| author_sort | Edi Marian Timofte |
| collection | DOAJ |
| description | The growing number of cyber threats and the implementation of stringent privacy regulations have revealed significant shortcomings in traditional centralized machine learning models, especially in distributed systems like the Internet of Things (IoT). This study presents a Federated Learning (FL) framework designed for intrusion detection and malware classification. This framework enables decentralized model training while preserving data locality and minimizing communication overhead. The proposed architecture incorporates lightweight, privacy-preserving techniques, including gradient clipping, differential privacy, and encrypted model aggregation, to ensure secure and efficient collaboration across heterogeneous clients. Experimental results on two widely adopted cybersecurity benchmarks demonstrate that the framework achieves detection accuracies above 90%, maintains privacy loss below 5%, and improves communication efficiency by over 25%. These results confirm the viability of FL as a scalable, privacy-compliant approach for next-generation cybersecurity systems in highly distributed infrastructures. |
| format | Article |
| id | doaj-art-2dc6aa1ac25a4be3a3e6aadc64739d95 |
| institution | Matheson Library |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-2dc6aa1ac25a4be3a3e6aadc64739d952025-06-25T13:26:43ZengMDPI AGApplied Sciences2076-34172025-06-011512687810.3390/app15126878Federated Learning for Cybersecurity: A Privacy-Preserving ApproachEdi Marian Timofte0Mihai Dimian1Adrian Graur2Alin Dan Potorac3Doru Balan4Ionut Croitoru5Daniel-Florin Hrițcan6Marcel Pușcașu7Department of Computers, Automation and Electronics, University “Ștefan cel Mare”, 720229 Suceava, RomaniaDepartment of Computers, Automation and Electronics, University “Ștefan cel Mare”, 720229 Suceava, RomaniaDepartment of Computers, Automation and Electronics, University “Ștefan cel Mare”, 720229 Suceava, RomaniaDepartment of Computers, Automation and Electronics, University “Ștefan cel Mare”, 720229 Suceava, RomaniaDepartment of Computers, Automation and Electronics, University “Ștefan cel Mare”, 720229 Suceava, RomaniaDepartment of Computers, Automation and Electronics, University “Ștefan cel Mare”, 720229 Suceava, RomaniaDepartment of Computers, Automation and Electronics, University “Ștefan cel Mare”, 720229 Suceava, RomaniaDepartment of Computers, Automation and Electronics, University “Ștefan cel Mare”, 720229 Suceava, RomaniaThe growing number of cyber threats and the implementation of stringent privacy regulations have revealed significant shortcomings in traditional centralized machine learning models, especially in distributed systems like the Internet of Things (IoT). This study presents a Federated Learning (FL) framework designed for intrusion detection and malware classification. This framework enables decentralized model training while preserving data locality and minimizing communication overhead. The proposed architecture incorporates lightweight, privacy-preserving techniques, including gradient clipping, differential privacy, and encrypted model aggregation, to ensure secure and efficient collaboration across heterogeneous clients. Experimental results on two widely adopted cybersecurity benchmarks demonstrate that the framework achieves detection accuracies above 90%, maintains privacy loss below 5%, and improves communication efficiency by over 25%. These results confirm the viability of FL as a scalable, privacy-compliant approach for next-generation cybersecurity systems in highly distributed infrastructures.https://www.mdpi.com/2076-3417/15/12/6878federated learningcybersecurityintrusion detectionprivacy preservationIoT securitymachine learning |
| spellingShingle | Edi Marian Timofte Mihai Dimian Adrian Graur Alin Dan Potorac Doru Balan Ionut Croitoru Daniel-Florin Hrițcan Marcel Pușcașu Federated Learning for Cybersecurity: A Privacy-Preserving Approach Applied Sciences federated learning cybersecurity intrusion detection privacy preservation IoT security machine learning |
| title | Federated Learning for Cybersecurity: A Privacy-Preserving Approach |
| title_full | Federated Learning for Cybersecurity: A Privacy-Preserving Approach |
| title_fullStr | Federated Learning for Cybersecurity: A Privacy-Preserving Approach |
| title_full_unstemmed | Federated Learning for Cybersecurity: A Privacy-Preserving Approach |
| title_short | Federated Learning for Cybersecurity: A Privacy-Preserving Approach |
| title_sort | federated learning for cybersecurity a privacy preserving approach |
| topic | federated learning cybersecurity intrusion detection privacy preservation IoT security machine learning |
| url | https://www.mdpi.com/2076-3417/15/12/6878 |
| work_keys_str_mv | AT edimariantimofte federatedlearningforcybersecurityaprivacypreservingapproach AT mihaidimian federatedlearningforcybersecurityaprivacypreservingapproach AT adriangraur federatedlearningforcybersecurityaprivacypreservingapproach AT alindanpotorac federatedlearningforcybersecurityaprivacypreservingapproach AT dorubalan federatedlearningforcybersecurityaprivacypreservingapproach AT ionutcroitoru federatedlearningforcybersecurityaprivacypreservingapproach AT danielflorinhritcan federatedlearningforcybersecurityaprivacypreservingapproach AT marcelpuscasu federatedlearningforcybersecurityaprivacypreservingapproach |