Application of differential privacy to sensor data in water quality monitoring task

被引:0
作者
Arzovs, Audris [1 ]
Parshutin, Sergei [2 ]
Urbanovics, Valts [3 ]
Rubulis, Janis [3 ]
Dejus, Sandis [3 ]
机构
[1] Inst Elect & Comp Sci, Riga, Latvia
[2] Riga Tech Univ, Inst Informat Technol, Riga, Latvia
[3] Riga Tech Univ, Water Syst & Biotechnol Inst, Riga, Latvia
关键词
Water quality monitoring; Differential privacy; Federated learning; CRITICAL INFRASTRUCTURE;
D O I
10.1016/j.ecoinf.2025.103019
中图分类号
Q14 [生态学(生物生态学)];
学科分类号
071012 ; 0713 ;
摘要
Although differential privacy (DP) is used to obfuscate local information and avoid data leakage, very little research exists on the neural network model performance with applied DP for datasets from online drinking water sensor monitoring. This study aims to examine the accuracy of four different neural network model architectures with DP applications. To compare the performance of the neural network model performance in total 2 215 906 augmented and experimentally obtained sensor readings were obtained from a drinking-water pilot system. Three types of contaminations at three different concentrations were applied as scenarios for anomalies in drinking water monitoring. The results achieved similar accuracy with all model architectures, with the best result showing only a 0.3% reduction in model accuracy compared with a nonprivate neural network model with 94% and 94.7% accuracy, respectively. Thus, differential privacy can be applied in the field of water quality monitoring with a reasonable decrease in the model performance.
引用
收藏
页数:11
相关论文
共 50 条
  • [41] Impact of inaccurate data on Differential Privacy
    Wang, Dong
    Xu, Zhengquan
    COMPUTERS & SECURITY, 2019, 82 : 68 - 79
  • [42] Bayesian Differential Privacy on Correlated Data
    Yang, Bin
    Sato, Issei
    Nakagawa, Hiroshi
    SIGMOD'15: PROCEEDINGS OF THE 2015 ACM SIGMOD INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2015, : 747 - 762
  • [43] Privacy preserving and data publication for vehicular trajectories with differential privacy
    Arif, Muhammad
    Chen, Jianer
    Wang, Guojun
    Geman, Oana
    Balas, Valentina Emilia
    MEASUREMENT, 2021, 173
  • [44] DynaPro: Dynamic Wireless Sensor Network Data Protection Algorithm in IoT via Differential Privacy
    Li, Songyan
    Liu, Zhaobin
    Huang, Zhiyi
    Lyu, Haoze
    Li, Zhiyang
    Liu, Weijiang
    IEEE ACCESS, 2019, 7 : 167754 - 167765
  • [45] SURFACE WATER QUALITY MONITORING AND EVALUATION BASED ON WIRELESS SENSOR NETWORK
    Luan, Xuede
    Sun, Hongwei
    FRESENIUS ENVIRONMENTAL BULLETIN, 2022, 31 (04): : 3893 - 3901
  • [46] A Biological Sensor System Using Computer Vision for Water Quality Monitoring
    Yuan, Fei
    Huang, Yifan
    Chen, Xin
    Cheng, En
    IEEE ACCESS, 2018, 6 : 61535 - 61546
  • [47] Differential Privacy for Data and Model Publishing of Medical Data
    Sun, Zongkun
    Wang, Yinglong
    Shu, Minglei
    Liu, Ruixia
    Zhao, Huiqi
    IEEE ACCESS, 2019, 7 : 152103 - 152114
  • [48] Application of privacy protection technology to healthcare big data
    Shin, Hyunah
    Ryu, Kyeongmin
    Kim, Jong-Yeup
    Lee, Suehyun
    DIGITAL HEALTH, 2024, 10
  • [49] Application of ion-sensitive sensors in water quality monitoring
    Winkler, S
    Rieger, L
    Saracevic, E
    Pressl, A
    Gruber, G
    WATER SCIENCE AND TECHNOLOGY, 2004, 50 (11) : 105 - 114
  • [50] Task-Specific Knowledge Distillation with Differential Privacy in LLMs
    Garg, Sonakshi
    Torra, Vicenc
    COMPUTER SECURITY-ESORICS 2024, PT II, 2024, 14983 : 374 - 389