Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385779903> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4385779903 endingPage "234" @default.
- W4385779903 startingPage "217" @default.
- W4385779903 abstract "Machine learning algorithms are proven to be vulnerable to model inversion and membership inference attacks, which raises much privacy concerns for its applications in sensitive scenarios. Typically, the state-of-the-art privacy preserving machine learning methods tend to provide privacy protection guarantee at the cost of losing data utility. This inevitably causes degradation of the model performance, especially for those tasks who are trained using small data sets. Therefore, optimizations on the trade-offs between individual privacy and data utility become a critical issue in machine learning. In this work, we proposed a privacy preserving machine learning algorithm RRML (Random Response Machine Learning) by combining the random response mechanism with the semi-supervised teachers-student learning way, and give the privacy analysis. Extensive experiments have been conducted to validate the effectiveness of RRML in addressing the above mentioned problem. The experimental results confirmed its superiority in balancing data utility and privacy against the state-of-the-art privacy preserving machine learning algorithms, especially in small data scenarios." @default.
- W4385779903 created "2023-08-13" @default.
- W4385779903 creator A5004719336 @default.
- W4385779903 creator A5037595255 @default.
- W4385779903 creator A5066935890 @default.
- W4385779903 date "2023-01-01" @default.
- W4385779903 modified "2023-10-16" @default.
- W4385779903 title "RRML: Privacy Preserving Machine Learning Based on Random Response Technology" @default.
- W4385779903 cites W2051267297 @default.
- W4385779903 cites W2053637704 @default.
- W4385779903 cites W2151961366 @default.
- W4385779903 cites W2473418344 @default.
- W4385779903 cites W2535690855 @default.
- W4385779903 cites W2591882872 @default.
- W4385779903 cites W2630997112 @default.
- W4385779903 cites W2757528734 @default.
- W4385779903 cites W2809414288 @default.
- W4385779903 cites W2811973125 @default.
- W4385779903 cites W2896069478 @default.
- W4385779903 cites W2905810301 @default.
- W4385779903 cites W2911978475 @default.
- W4385779903 cites W2930926105 @default.
- W4385779903 cites W2947134462 @default.
- W4385779903 cites W2962835266 @default.
- W4385779903 cites W2964010366 @default.
- W4385779903 cites W2964151798 @default.
- W4385779903 cites W2964162474 @default.
- W4385779903 cites W3022746105 @default.
- W4385779903 cites W3098949126 @default.
- W4385779903 cites W3099185017 @default.
- W4385779903 doi "https://doi.org/10.1007/978-3-031-39828-5_12" @default.
- W4385779903 hasPublicationYear "2023" @default.
- W4385779903 type Work @default.
- W4385779903 citedByCount "0" @default.
- W4385779903 crossrefType "book-chapter" @default.
- W4385779903 hasAuthorship W4385779903A5004719336 @default.
- W4385779903 hasAuthorship W4385779903A5037595255 @default.
- W4385779903 hasAuthorship W4385779903A5066935890 @default.
- W4385779903 hasConcept C115903097 @default.
- W4385779903 hasConcept C119857082 @default.
- W4385779903 hasConcept C123201435 @default.
- W4385779903 hasConcept C154945302 @default.
- W4385779903 hasConcept C2776214188 @default.
- W4385779903 hasConcept C38652104 @default.
- W4385779903 hasConcept C41008148 @default.
- W4385779903 hasConcept C77967617 @default.
- W4385779903 hasConceptScore W4385779903C115903097 @default.
- W4385779903 hasConceptScore W4385779903C119857082 @default.
- W4385779903 hasConceptScore W4385779903C123201435 @default.
- W4385779903 hasConceptScore W4385779903C154945302 @default.
- W4385779903 hasConceptScore W4385779903C2776214188 @default.
- W4385779903 hasConceptScore W4385779903C38652104 @default.
- W4385779903 hasConceptScore W4385779903C41008148 @default.
- W4385779903 hasConceptScore W4385779903C77967617 @default.
- W4385779903 hasLocation W43857799031 @default.
- W4385779903 hasOpenAccess W4385779903 @default.
- W4385779903 hasPrimaryLocation W43857799031 @default.
- W4385779903 hasRelatedWork W2792987183 @default.
- W4385779903 hasRelatedWork W2954428433 @default.
- W4385779903 hasRelatedWork W2973458857 @default.
- W4385779903 hasRelatedWork W3094076422 @default.
- W4385779903 hasRelatedWork W3196155444 @default.
- W4385779903 hasRelatedWork W3209574120 @default.
- W4385779903 hasRelatedWork W4306321456 @default.
- W4385779903 hasRelatedWork W4306674287 @default.
- W4385779903 hasRelatedWork W4319309271 @default.
- W4385779903 hasRelatedWork W4224009465 @default.
- W4385779903 isParatext "false" @default.
- W4385779903 isRetracted "false" @default.
- W4385779903 workType "book-chapter" @default.