How unique is weekly smart meter data?
Abstract In many countries, energy consumption data is collected through smart meters in 15-min intervals. Prior work has shown that 1 year’s worth of this data is sufficient to extract sensitive information about households. In this short paper, we break down energy consumption data from a novel da...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-09-01
|
| Series: | Energy Informatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42162-022-00205-8 |
| _version_ | 1828418607849144320 |
|---|---|
| author | Dejan Radovanovic Andreas Unterweger Günther Eibl Dominik Engel Johannes Reichl |
| author_facet | Dejan Radovanovic Andreas Unterweger Günther Eibl Dominik Engel Johannes Reichl |
| author_sort | Dejan Radovanovic |
| collection | DOAJ |
| description | Abstract In many countries, energy consumption data is collected through smart meters in 15-min intervals. Prior work has shown that 1 year’s worth of this data is sufficient to extract sensitive information about households. In this short paper, we break down energy consumption data from a novel dataset into 1-week snippets. Using off-the-shelf algorithms, we assess whether it is possible to clearly identify (i.e., fingerprint) an individual household only by its energy consumption from a 1-week period. More generally, we ask whether an attacker can distinguish one household from a group of others by its energy consumption from only one week’s worth of data. We find that a small number of households exist for which the weekly consumption is so unique that it can be distinguished almost always amidst weekly data from dozens of other households. Furthermore, a large number of households can be distinguished with surprisingly high accuracy and an order of magnitude better than guessing. We discuss the potential impact of these findings on the privacy of smart meter datasets with respect to de-anonymization and re-identifiability. |
| first_indexed | 2024-12-10T14:40:38Z |
| format | Article |
| id | doaj.art-c00d2ea576f34a65b887687c19b3eb6d |
| institution | Directory Open Access Journal |
| issn | 2520-8942 |
| language | English |
| last_indexed | 2024-12-10T14:40:38Z |
| publishDate | 2022-09-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Energy Informatics |
| spelling | doaj.art-c00d2ea576f34a65b887687c19b3eb6d2022-12-22T01:44:43ZengSpringerOpenEnergy Informatics2520-89422022-09-015S111010.1186/s42162-022-00205-8How unique is weekly smart meter data?Dejan Radovanovic0Andreas Unterweger1Günther Eibl2Dominik Engel3Johannes Reichl4Center for Secure Energy InformaticsCenter for Secure Energy InformaticsCenter for Secure Energy InformaticsCenter for Secure Energy InformaticsEnergieinstitut an der Johannes Kepler Universität LinzAbstract In many countries, energy consumption data is collected through smart meters in 15-min intervals. Prior work has shown that 1 year’s worth of this data is sufficient to extract sensitive information about households. In this short paper, we break down energy consumption data from a novel dataset into 1-week snippets. Using off-the-shelf algorithms, we assess whether it is possible to clearly identify (i.e., fingerprint) an individual household only by its energy consumption from a 1-week period. More generally, we ask whether an attacker can distinguish one household from a group of others by its energy consumption from only one week’s worth of data. We find that a small number of households exist for which the weekly consumption is so unique that it can be distinguished almost always amidst weekly data from dozens of other households. Furthermore, a large number of households can be distinguished with surprisingly high accuracy and an order of magnitude better than guessing. We discuss the potential impact of these findings on the privacy of smart meter datasets with respect to de-anonymization and re-identifiability.https://doi.org/10.1186/s42162-022-00205-8Smart meterPrivacyData analysisAttack |
| spellingShingle | Dejan Radovanovic Andreas Unterweger Günther Eibl Dominik Engel Johannes Reichl How unique is weekly smart meter data? Energy Informatics Smart meter Privacy Data analysis Attack |
| title | How unique is weekly smart meter data? |
| title_full | How unique is weekly smart meter data? |
| title_fullStr | How unique is weekly smart meter data? |
| title_full_unstemmed | How unique is weekly smart meter data? |
| title_short | How unique is weekly smart meter data? |
| title_sort | how unique is weekly smart meter data |
| topic | Smart meter Privacy Data analysis Attack |
| url | https://doi.org/10.1186/s42162-022-00205-8 |
| work_keys_str_mv | AT dejanradovanovic howuniqueisweeklysmartmeterdata AT andreasunterweger howuniqueisweeklysmartmeterdata AT gunthereibl howuniqueisweeklysmartmeterdata AT dominikengel howuniqueisweeklysmartmeterdata AT johannesreichl howuniqueisweeklysmartmeterdata |