Privacy Auditing in Differential Private Machine Learning: The Current Trends
Differential privacy has recently gained prominence, especially in the context of private machine learning. While the definition of differential privacy makes it possible to provably limit the amount of information leaked by an algorithm, practical implementations of differentially private algorithm...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/647 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589265625677824 |
|---|---|
| author | Ivars Namatevs Kaspars Sudars Arturs Nikulins Kaspars Ozols |
| author_facet | Ivars Namatevs Kaspars Sudars Arturs Nikulins Kaspars Ozols |
| author_sort | Ivars Namatevs |
| collection | DOAJ |
| description | Differential privacy has recently gained prominence, especially in the context of private machine learning. While the definition of differential privacy makes it possible to provably limit the amount of information leaked by an algorithm, practical implementations of differentially private algorithms often contain subtle vulnerabilities. Therefore, there is a need for effective methods that can audit <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mi>ϵ</mi><mo>,</mo><mi>δ</mi><mo>)</mo></mrow></semantics></math></inline-formula> differentially private algorithms before they are deployed in the real world. The article examines studies that recommend privacy guarantees for differential private machine learning. It covers a wide range of topics on the subject and provides comprehensive guidance for privacy auditing schemes based on privacy attacks to protect machine-learning models from privacy leakage. Our results contribute to the growing literature on differential privacy in the realm of privacy auditing and beyond and pave the way for future research in the field of privacy-preserving models. |
| format | Article |
| id | doaj-art-7077c1872c164b7a8d99a1c71c614433 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-7077c1872c164b7a8d99a1c71c6144332025-01-24T13:20:16ZengMDPI AGApplied Sciences2076-34172025-01-0115264710.3390/app15020647Privacy Auditing in Differential Private Machine Learning: The Current TrendsIvars Namatevs0Kaspars Sudars1Arturs Nikulins2Kaspars Ozols3Institute of Electronics and Computer Science, 14 Dzerbenes St., LV-1006 Riga, LatviaInstitute of Electronics and Computer Science, 14 Dzerbenes St., LV-1006 Riga, LatviaInstitute of Electronics and Computer Science, 14 Dzerbenes St., LV-1006 Riga, LatviaInstitute of Electronics and Computer Science, 14 Dzerbenes St., LV-1006 Riga, LatviaDifferential privacy has recently gained prominence, especially in the context of private machine learning. While the definition of differential privacy makes it possible to provably limit the amount of information leaked by an algorithm, practical implementations of differentially private algorithms often contain subtle vulnerabilities. Therefore, there is a need for effective methods that can audit <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mi>ϵ</mi><mo>,</mo><mi>δ</mi><mo>)</mo></mrow></semantics></math></inline-formula> differentially private algorithms before they are deployed in the real world. The article examines studies that recommend privacy guarantees for differential private machine learning. It covers a wide range of topics on the subject and provides comprehensive guidance for privacy auditing schemes based on privacy attacks to protect machine-learning models from privacy leakage. Our results contribute to the growing literature on differential privacy in the realm of privacy auditing and beyond and pave the way for future research in the field of privacy-preserving models.https://www.mdpi.com/2076-3417/15/2/647differential privacydifferential private machine learningdifferential privacy auditingprivacy attacks |
| spellingShingle | Ivars Namatevs Kaspars Sudars Arturs Nikulins Kaspars Ozols Privacy Auditing in Differential Private Machine Learning: The Current Trends Applied Sciences differential privacy differential private machine learning differential privacy auditing privacy attacks |
| title | Privacy Auditing in Differential Private Machine Learning: The Current Trends |
| title_full | Privacy Auditing in Differential Private Machine Learning: The Current Trends |
| title_fullStr | Privacy Auditing in Differential Private Machine Learning: The Current Trends |
| title_full_unstemmed | Privacy Auditing in Differential Private Machine Learning: The Current Trends |
| title_short | Privacy Auditing in Differential Private Machine Learning: The Current Trends |
| title_sort | privacy auditing in differential private machine learning the current trends |
| topic | differential privacy differential private machine learning differential privacy auditing privacy attacks |
| url | https://www.mdpi.com/2076-3417/15/2/647 |
| work_keys_str_mv | AT ivarsnamatevs privacyauditingindifferentialprivatemachinelearningthecurrenttrends AT kasparssudars privacyauditingindifferentialprivatemachinelearningthecurrenttrends AT artursnikulins privacyauditingindifferentialprivatemachinelearningthecurrenttrends AT kasparsozols privacyauditingindifferentialprivatemachinelearningthecurrenttrends |