Federated Learning Approaches for Privacy-Preserving Threat Detection in Smart Home IoT Environments
Bibliographic record
Abstract
Smart home Internet of Things (IoT) environments have become increasingly pervasive, offering convenience and automation while simultaneously introducing new cybersecurity vulnerabilities. Traditional centralized machine learning approaches for threat detection rely on aggregating sensitive user data into cloud servers, raising significant concerns regarding privacy, data security, and regulatory compliance. Federated learning (FL) has emerged as a promising paradigm that enables collaborative model training across distributed IoT devices without sharing raw data, thus preserving privacy while maintaining effective threat detection. This review paper explores the application of FL in privacy-preserving threat detection within smart home IoT systems, analyzing its strengths, limitations, and future potential. The discussion highlights how FL mitigates risks such as data leakage, adversarial attacks, and model inversion while ensuring scalability in heterogeneous device ecosystems. Moreover, the review examines existing frameworks, comparative case studies, and integration with complementary technologies like blockchain and differential privacy to enhance robustness. Challenges such as communication overhead, resource constraints, and model poisoning attacks are also critically addressed. By synthesizing recent advancements and identifying open research gaps, this paper provides a roadmap for leveraging FL in developing secure, scalable, and privacy-preserving threat detection systems for smart homes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.009 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.004 | 0.008 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".