Aktuálne číslo: 1/2026
Archív
DATA ANONYMIZATION IN WASTE MANAGEMENT: CHALLENGES, METHODS, AND AI-DRIVEN APPROACHES
The digital transformation of waste management systems—encompassing Radio Frequency Identification (RFID)-equipped collection bins, Global Positioning System (GPS)-tracked vehicles, sensor-based smart containers, and pay-as-you-throw (PAYT) billing—generates continuous streams of data that carry significant privacy implications. These data intersect personal, commercial, and operational interests of municipalities, citizens, waste-collection companies, producer responsibility organisations (PROs), regulators, and researchers. Waste management presents sector-specific challenges that remain underexplored: the physical tangibility of waste enables re-identification even after digital anonymization; PAYT systems expose household behavioural patterns; and industrial waste data constitute commercially protected trade secrets. This paper analyses the anonymization requirements of all major stakeholder groups, reviews legal obligations, and proposes a layered anonymization workflow grounded in operational practice at waste-collection operators. Both classical and emerging AI-driven techniques are evaluated—including differential privacy, NLP/NER-based document redaction, OCR pipelines, computer-vision anonymization, Vision-Language Models (VLMs), agentic LLM pipelines, synthetic data generation, and federated learning. A strict requirement for all AI-driven methods is on-premise deployment. A comparative analysis against water, energy, and telecommunications utilities highlights what makes waste data unique.
Vydanie: 2026/1 Strany: 77-87 Klasifikácia JEL: Q53, K32, O33
DOI: https://doi.org/10.52665/ser20260106
Kľúčové slová: data anonymization; waste management; PAYT; differential privacy; privacy by design
Sekcia: Special section - Scientific articles from the international scientific conference "ECOSYSTEMS OF THE FUTURE: Startups, Smart Cities and Human Resources at the Core of the Digital Economy"
Kontakty:
Marcel Linek, D2B s.r.o.
Bratislava, Slovakia
e-mail: marcel.linek@d2b.sk
Petra Bobíková, Asseco Central Europe, a. s.
Bratislava, Slovakia
e-mail: petra.bobikova@asseco-ce.com
Mgr. Pavol Petrovič, PhD., Asseco Central Europe, a.s.
Bratislava, Slovakia
e-mail: pavol.petrovic@asseco-ce.com
Roman Rigó, Asseco Central Europe, a. s.
Bratislava, Slovakia
e-mail: roman.rigo@asseco-ce.com
Marek Belička, Asseco Central Europe, a. s.
Bratislava, Slovakia
e-mail: marek.belicka@asseco-ce.com
Literatúra:
Angus, A. and Duan, Z. (2022). Real-time video anonymization in smart city intersections. In Proceedings of the IEEE MASS Conference.
Bertino, E. and Sandhu, R. (2005). Database security—concepts, approaches, and challenges. IEEE Transactions on Dependable and Secure Computing, 2(1), 2–19. https://doi.org/10.1109/TDSC.2005.9
Brighente, A., Conti, M., Di Renzone, G. and Peruzzi, G. (2023). Security and privacy of smart waste management systems: A cyber-physical system perspective. IEEE Internet of Things Journal, 10(10), 8580–8592. https://doi.org/10.1109/JIOT.2023.3322532
Duchi, J. C., Jordan, M. I. and Wainwright, M. J. (2013). Local privacy and statistical minimax rates. In Proceedings of the IEEE FOCS, 429–438. https://doi.org/10.1109/FOCS.2013.53
Dwork, C., McSherry, F., Nissim, K. and Smith, A. (2006). Calibrating noise to sensitivity in private data analysis. In Proceedings of TCC, LNCS vol. 3876, 265–284. https://doi.org/10.1007/11681878\_14
EDPB (2020). Guidelines 01/2020 on Processing Personal Data in the Context of Connected Vehicles and Mobility Related Applications. European Data Protection Board, Brussels.
Kaur, R. et al. (2025). A survey on privacy preservation techniques in IoT systems. Sensors, 25(22), 6967. https://doi.org/10.3390/s25226967
Liu, X., Heller, A. and Nielsen, P. S. (2017). CITIESData: A smart city data management framework. Knowledge and Information Systems, 53(3), 699–722. https://doi.org/10.1007/s10115-017-1051-3
Maximov, M., Elezi, I. and Leal-Taixé, L. (2020). CIAGAN: Conditional identity anonymization generative adversarial networks. In Proceedings of the IEEE CVPR. arXiv:2005.09544
Muştu, M. İ. and Ekenel, H. K. (2025). Assessing the use of face swapping methods as face anonymizers in videos. arXiv preprint arXiv:2501.04955.
Ribačič, S. and Fratrič, I. (2016). De-identification for privacy protection in multimedia content: A survey. Signal Processing: Image Communication, 47, 131–151. https://doi.org/10.1016/j.image.2016.05.020
Sampaio, S. et al. (2023). Collecting, processing and secondary using personal and (pseudo)anonymized data in smart cities. Applied Sciences, 13(6), 3830. https://doi.org/10.3390/app13063830
Slovak Environmental Agency (SŽP) (2023). Report on the State of the Environment of the Slovak Republic. Ministry of the Environment of the Slovak Republic, Banská Bystrica.
Sweeney, L. (2002). k-Anonymity: A model for protecting privacy. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 10(5), 557–570. https://doi.org/10.1142/S0218488502001648
Zhang, Z., Cilloni, T., Walter, C. and Fleming, C. (2021). Multi-scale, class-generic, privacy-preserving video. Electronics, 10(10), 1172. https://doi.org/10.3390/electronics10101172