Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328114468> ?p ?o ?g. }
- W4328114468 endingPage "2203" @default.
- W4328114468 startingPage "2192" @default.
- W4328114468 abstract "Abstract The wide application of image classification has given rise to many intelligent systems, such as face recognition systems, which makes our life more convenient. However, the ensuing privacy leakage problem has become increasingly serious. The training of a deep neural network requires lots of data, which may contain sensitive information of users and may be exploited by data collectors. A perturbation algorithm named RRN is proposed for image data based on local differential privacy, which provides a rigorous privacy guarantee. Existing solutions have low accuracy due to the high sensitivity of an image; the authors' method combines the Randomized Response mechanism with the Laplace mechanism to solve this problem. Experiments were conducted on the MNIST and CIFAR‐10 datasets to show the effectiveness of the algorithm. Experimental results shows that the model is better than baseline models. The algorithm was also implemented on the commonly used model in deep learning, the VGG model, which can achieve 96.4% accuracy in the non‐private version on the CIFAR‐10 dataset. The accuracy of the differential private VGG model based on the RRN algorithm is 83% when , which is still excellent. The experimental results show that the RRN algorithm can both preserve privacy and data utility." @default.
- W4328114468 created "2023-03-22" @default.
- W4328114468 creator A5007042457 @default.
- W4328114468 creator A5051811819 @default.
- W4328114468 creator A5058161586 @default.
- W4328114468 creator A5067980532 @default.
- W4328114468 date "2023-03-20" @default.
- W4328114468 modified "2023-10-05" @default.
- W4328114468 title "RRN: A differential private approach to preserve privacy in image classification" @default.
- W4328114468 cites W1485110750 @default.
- W4328114468 cites W1557833142 @default.
- W4328114468 cites W1677182931 @default.
- W4328114468 cites W1873763122 @default.
- W4328114468 cites W1966072539 @default.
- W4328114468 cites W2013823004 @default.
- W4328114468 cites W2051267297 @default.
- W4328114468 cites W2135930857 @default.
- W4328114468 cites W2473418344 @default.
- W4328114468 cites W2520442116 @default.
- W4328114468 cites W2534826340 @default.
- W4328114468 cites W2535690855 @default.
- W4328114468 cites W2799331111 @default.
- W4328114468 cites W2889785340 @default.
- W4328114468 cites W2890880325 @default.
- W4328114468 cites W2891311364 @default.
- W4328114468 cites W2911915417 @default.
- W4328114468 cites W2911978475 @default.
- W4328114468 cites W2930558539 @default.
- W4328114468 cites W2949162041 @default.
- W4328114468 cites W2956998997 @default.
- W4328114468 cites W2963313259 @default.
- W4328114468 cites W2963366347 @default.
- W4328114468 cites W2963629772 @default.
- W4328114468 cites W2963699739 @default.
- W4328114468 cites W2963881987 @default.
- W4328114468 cites W2963952467 @default.
- W4328114468 cites W2965783911 @default.
- W4328114468 cites W2985158452 @default.
- W4328114468 cites W2986151549 @default.
- W4328114468 cites W2989394982 @default.
- W4328114468 cites W3027483882 @default.
- W4328114468 cites W3100637409 @default.
- W4328114468 cites W3101886934 @default.
- W4328114468 cites W3102360395 @default.
- W4328114468 cites W3102407811 @default.
- W4328114468 cites W3102834148 @default.
- W4328114468 cites W3110619060 @default.
- W4328114468 cites W3200400919 @default.
- W4328114468 cites W4205228770 @default.
- W4328114468 cites W4214873788 @default.
- W4328114468 cites W4290960278 @default.
- W4328114468 doi "https://doi.org/10.1049/ipr2.12784" @default.
- W4328114468 hasPublicationYear "2023" @default.
- W4328114468 type Work @default.
- W4328114468 citedByCount "1" @default.
- W4328114468 crossrefType "journal-article" @default.
- W4328114468 hasAuthorship W4328114468A5007042457 @default.
- W4328114468 hasAuthorship W4328114468A5051811819 @default.
- W4328114468 hasAuthorship W4328114468A5058161586 @default.
- W4328114468 hasAuthorship W4328114468A5067980532 @default.
- W4328114468 hasBestOaLocation W43281144681 @default.
- W4328114468 hasConcept C105795698 @default.
- W4328114468 hasConcept C11413529 @default.
- W4328114468 hasConcept C115961682 @default.
- W4328114468 hasConcept C119857082 @default.
- W4328114468 hasConcept C124101348 @default.
- W4328114468 hasConcept C153180895 @default.
- W4328114468 hasConcept C154945302 @default.
- W4328114468 hasConcept C185429906 @default.
- W4328114468 hasConcept C190502265 @default.
- W4328114468 hasConcept C23130292 @default.
- W4328114468 hasConcept C2776441110 @default.
- W4328114468 hasConcept C3017597292 @default.
- W4328114468 hasConcept C33923547 @default.
- W4328114468 hasConcept C38652104 @default.
- W4328114468 hasConcept C41008148 @default.
- W4328114468 hasConcept C50644808 @default.
- W4328114468 hasConceptScore W4328114468C105795698 @default.
- W4328114468 hasConceptScore W4328114468C11413529 @default.
- W4328114468 hasConceptScore W4328114468C115961682 @default.
- W4328114468 hasConceptScore W4328114468C119857082 @default.
- W4328114468 hasConceptScore W4328114468C124101348 @default.
- W4328114468 hasConceptScore W4328114468C153180895 @default.
- W4328114468 hasConceptScore W4328114468C154945302 @default.
- W4328114468 hasConceptScore W4328114468C185429906 @default.
- W4328114468 hasConceptScore W4328114468C190502265 @default.
- W4328114468 hasConceptScore W4328114468C23130292 @default.
- W4328114468 hasConceptScore W4328114468C2776441110 @default.
- W4328114468 hasConceptScore W4328114468C3017597292 @default.
- W4328114468 hasConceptScore W4328114468C33923547 @default.
- W4328114468 hasConceptScore W4328114468C38652104 @default.
- W4328114468 hasConceptScore W4328114468C41008148 @default.
- W4328114468 hasConceptScore W4328114468C50644808 @default.
- W4328114468 hasIssue "7" @default.
- W4328114468 hasLocation W43281144681 @default.
- W4328114468 hasOpenAccess W4328114468 @default.
- W4328114468 hasPrimaryLocation W43281144681 @default.
- W4328114468 hasRelatedWork W2089093487 @default.