Privacy-Preserving Data Anonymization for IoT: A Strategy Selection Framework

The widespread use of Internet of Things (IoT) devices generates large volumes of sensitive, fine-grained data, heightening privacy risks. Traditional anonymization methods struggle to balance privacy and utility for high-dimensional, noisy IoT data. This paper proposes an RFD-based optimization framework that employs Relaxed Functional Dependencies (RFDs) to model relationships among quasi-identifiers and create context-aware anonymization strategies. An optimization-driven evaluation balances k-anonymity with data utility to maintain analytical value. Using the Bot-IoT dataset, a benchmark in IoT privacy research, experiments show that the proposed method achieves stronger privacy protection with lower information loss than conventional approaches. The framework offers a scalable and adaptive solution for privacy-preserving IoT data publishing, applicable to smart homes, healthcare monitoring, and other connected environments.

Cite as:

@INPROCEEDINGS{11297691,
  author={Sadeghi-Nasab, Alireza and Rahmani, Mohsen},
  booktitle={2025 9th International Conference on Internet of Things and Applications (IoT)}, 
  title={Privacy-Preserving Data Anonymization for IoT: A Strategy Selection Framework}, 
  year={2025},
  volume={},
  number={},
  pages={1-6},
  keywords={Data privacy;Publishing;Scalability;Smart homes;Information filtering;Internet of Things;Particle swarm optimization;Protection;Optimization;Information integrity;Internet of Things;Data anonymization;Privacy preserving;Relaxed functional dependencies;Particle swarm optimization;k-anonymity},
  doi={10.1109/IoT69654.2025.11297691}
}