Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385270209> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4385270209 abstract "In this paper, we present how Differential Privacy (DP), the recent state-of-the-art privacy-preserving technologies, plays a role with four different Machine Learning (ML) classifiers. Preserving privacy while serving utility needs is a challenge for each ML implementation. To study the effects of different DP implementations on an ML method, we do perturbation at different phases of the ML cycle, such as perturbing data at its origin (Differential Privacy Method 1 - DPM1), during the training process (DPM2) or perturbing the parameters of the ML model generated (DPM3) and see the effect of privacy preservation on ML model utility. Further, we have tested with different perturbation methods such as the Laplace, Gaussian, Analytic Gaussian, Snapping, and Staircase mechanisms for DPM1 and analysed the results to know which one works better. We tested each case considered with varying privacy budgets. We have used privacy attacks such as the Membership Inference Attack (MIA) and the Attribute Inference Attack (AIA) to see the DP’s effect in protecting data privacy. Our experiment’s results showed that perturbing at later stages of an ML method provides better utility. When considering different DPM1 mechanisms, improved Laplace and Gaussian versions work better in utility while preserving privacy." @default.
- W4385270209 created "2023-07-27" @default.
- W4385270209 creator A5036679430 @default.
- W4385270209 creator A5058096999 @default.
- W4385270209 creator A5059640195 @default.
- W4385270209 creator A5083253222 @default.
- W4385270209 date "2023-06-21" @default.
- W4385270209 modified "2023-09-25" @default.
- W4385270209 title "Privacy vs Utility analysis when applying Differential Privacy on Machine Learning Classifiers" @default.
- W4385270209 doi "https://doi.org/10.1109/wimob58348.2023.10187829" @default.
- W4385270209 hasPublicationYear "2023" @default.
- W4385270209 type Work @default.
- W4385270209 citedByCount "0" @default.
- W4385270209 crossrefType "proceedings-article" @default.
- W4385270209 hasAuthorship W4385270209A5036679430 @default.
- W4385270209 hasAuthorship W4385270209A5058096999 @default.
- W4385270209 hasAuthorship W4385270209A5059640195 @default.
- W4385270209 hasAuthorship W4385270209A5083253222 @default.
- W4385270209 hasConcept C119857082 @default.
- W4385270209 hasConcept C121332964 @default.
- W4385270209 hasConcept C123201435 @default.
- W4385270209 hasConcept C124101348 @default.
- W4385270209 hasConcept C134306372 @default.
- W4385270209 hasConcept C154945302 @default.
- W4385270209 hasConcept C163716315 @default.
- W4385270209 hasConcept C183057437 @default.
- W4385270209 hasConcept C199360897 @default.
- W4385270209 hasConcept C23130292 @default.
- W4385270209 hasConcept C26713055 @default.
- W4385270209 hasConcept C2776214188 @default.
- W4385270209 hasConcept C3017597292 @default.
- W4385270209 hasConcept C33923547 @default.
- W4385270209 hasConcept C38652104 @default.
- W4385270209 hasConcept C41008148 @default.
- W4385270209 hasConcept C61326573 @default.
- W4385270209 hasConcept C62520636 @default.
- W4385270209 hasConcept C97937538 @default.
- W4385270209 hasConceptScore W4385270209C119857082 @default.
- W4385270209 hasConceptScore W4385270209C121332964 @default.
- W4385270209 hasConceptScore W4385270209C123201435 @default.
- W4385270209 hasConceptScore W4385270209C124101348 @default.
- W4385270209 hasConceptScore W4385270209C134306372 @default.
- W4385270209 hasConceptScore W4385270209C154945302 @default.
- W4385270209 hasConceptScore W4385270209C163716315 @default.
- W4385270209 hasConceptScore W4385270209C183057437 @default.
- W4385270209 hasConceptScore W4385270209C199360897 @default.
- W4385270209 hasConceptScore W4385270209C23130292 @default.
- W4385270209 hasConceptScore W4385270209C26713055 @default.
- W4385270209 hasConceptScore W4385270209C2776214188 @default.
- W4385270209 hasConceptScore W4385270209C3017597292 @default.
- W4385270209 hasConceptScore W4385270209C33923547 @default.
- W4385270209 hasConceptScore W4385270209C38652104 @default.
- W4385270209 hasConceptScore W4385270209C41008148 @default.
- W4385270209 hasConceptScore W4385270209C61326573 @default.
- W4385270209 hasConceptScore W4385270209C62520636 @default.
- W4385270209 hasConceptScore W4385270209C97937538 @default.
- W4385270209 hasLocation W43852702091 @default.
- W4385270209 hasOpenAccess W4385270209 @default.
- W4385270209 hasPrimaryLocation W43852702091 @default.
- W4385270209 hasRelatedWork W173622546 @default.
- W4385270209 hasRelatedWork W2073199034 @default.
- W4385270209 hasRelatedWork W3005947044 @default.
- W4385270209 hasRelatedWork W3154070777 @default.
- W4385270209 hasRelatedWork W3206245744 @default.
- W4385270209 hasRelatedWork W3206966921 @default.
- W4385270209 hasRelatedWork W4206698993 @default.
- W4385270209 hasRelatedWork W4312054394 @default.
- W4385270209 hasRelatedWork W4313681213 @default.
- W4385270209 hasRelatedWork W4377712905 @default.
- W4385270209 isParatext "false" @default.
- W4385270209 isRetracted "false" @default.
- W4385270209 workType "article" @default.