Enhancing IoT privacy with artificial intelligence: Recent advances and future directions
Bibliographic record
Abstract
The proliferation of Internet of Things (IoT) devices has brought tremendous convenience in our daily lives but has also brought significant privacy concerns. In recent years, many solutions have been found in the literature to address these challenges through advanced technologies such as Artificial Intelligence (AI). This paper aims to provide a comprehensive survey of the current landscape of IoT privacy, focusing on the role of AI in enhancing privacy measures. We categorize critical privacy challenges, outline AI strategies to address these challenges, and present AI-driven solutions that have shown real and substantial results in major sectors. We examine various AI techniques, assess their effectiveness, and highlight existing research gaps to inform future researchers. Our main contributions include a taxonomy of AI applications for IoT privacy, an analysis of AI-driven privacy solutions, and a discussion on the ethical implications and compliance requirements. This paper is recommended to researchers, practitioners, and policymakers seeking to develop secure and privacy-aware IoT systems. Unlike previous surveys that analyze thoroughly individual privacy-preserving methods, this study provides a multi layer synthesis of AI techniques tailored to IoT architectures and deployment realities, presenting a taxonomy grounded in both theoretical robustness and implementation feasibility.
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 | 0.007 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.001 | 0.005 |
| Scholarly communication | 0.005 | 0.014 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.004 | 0.005 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".