Abstract
IoT devices are increasingly targeted by sophisticated malware, while data privacy constraints make centralised malware detection unsuitable for distributed environments. This paper presents Fed-BLAM, a federated learning framework that integrates parameter-efficient fine-tuning of pre-trained BERT and LLaMA models using low-rank adaptation (LoRA) for IoT malware detection. Distributed clients collaboratively train a shared model without exchanging raw network traffic, supporting privacy-preserving learning across heterogeneous devices. The proposed approach is evaluated using the N-BaIoT and TON-IoT datasets under balanced, highly imbalanced, and non-IID data distributions to emulate realistic deployment scenarios. Experimental results demonstrate that the federated LLM-based models consistently outperform a multilayer perceptron baseline, with the LLaMA model achieving up to 99.9% accuracy and F1-score while generalising effectively to previously unseen device types. These findings demonstrate the potential of combining federated learning and large language models for accurate, privacy-aware IoT malware detection in heterogeneous edge environments.
| Original language | English |
|---|---|
| Article number | 616 |
| Number of pages | 23 |
| Journal | The Journal of Supercomputing |
| Volume | 82 |
| Issue number | 616 |
| DOIs | |
| Publication status | Published - 10 Aug 2026 |
Keywords
- Federated Learning
- IoT Malware
- Large Language Models
- BERT
- LLaMA
Fingerprint
Dive into the research topics of 'Fed-blam: federated BERT and LLaMA for IoT malware detection'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver