Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304698924> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4304698924 abstract "Machine Learning (ML) has achieved enormous success in solving a variety of problems in computer vision, speech recognition, object detection, to name a few. The principal reason for this success is the availability of huge datasets for training deep neural networks (DNNs). However, datasets can not be publicly released if they contain sensitive information such as medical or financial records. In such cases, data privacy becomes a major concern. Encryption methods offer a possible solution to this issue, however their deployment on ML applications is non-trivial, as they seriously impact the classification accuracy and result in substantial computational overhead.Alternatively, obfuscation techniques can be used, but maintaining a good balance between visual privacy and accuracy is challenging. In this work, we propose a method to generate secure synthetic datasets from the original private datasets. In our method, given a network with Batch Normalization (BN) layers pre-trained on the original dataset, we first record the layer-wise BN statistics. Next, using the BN statistics and the pre-trained model, we generate the synthetic dataset by optimizing random noises such that the synthetic data match the layer-wise statistical distribution of the original model. We evaluate our method on image classification dataset (CIFAR10) and show that our synthetic data can be used for training networks from scratch, producing reasonable classification performance." @default.
- W4304698924 created "2022-10-12" @default.
- W4304698924 creator A5006180800 @default.
- W4304698924 creator A5031161187 @default.
- W4304698924 creator A5031719209 @default.
- W4304698924 date "2022-10-06" @default.
- W4304698924 modified "2023-09-23" @default.
- W4304698924 title "Synthetic Dataset Generation for Privacy-Preserving Machine Learning" @default.
- W4304698924 doi "https://doi.org/10.48550/arxiv.2210.03205" @default.
- W4304698924 hasPublicationYear "2022" @default.
- W4304698924 type Work @default.
- W4304698924 citedByCount "0" @default.
- W4304698924 crossrefType "posted-content" @default.
- W4304698924 hasAuthorship W4304698924A5006180800 @default.
- W4304698924 hasAuthorship W4304698924A5031161187 @default.
- W4304698924 hasAuthorship W4304698924A5031719209 @default.
- W4304698924 hasBestOaLocation W43046989241 @default.
- W4304698924 hasConcept C111919701 @default.
- W4304698924 hasConcept C119857082 @default.
- W4304698924 hasConcept C124101348 @default.
- W4304698924 hasConcept C136886441 @default.
- W4304698924 hasConcept C144024400 @default.
- W4304698924 hasConcept C148730421 @default.
- W4304698924 hasConcept C154945302 @default.
- W4304698924 hasConcept C162984825 @default.
- W4304698924 hasConcept C19165224 @default.
- W4304698924 hasConcept C2779960059 @default.
- W4304698924 hasConcept C38652104 @default.
- W4304698924 hasConcept C40305131 @default.
- W4304698924 hasConcept C41008148 @default.
- W4304698924 hasConcept C50644808 @default.
- W4304698924 hasConcept C73555534 @default.
- W4304698924 hasConceptScore W4304698924C111919701 @default.
- W4304698924 hasConceptScore W4304698924C119857082 @default.
- W4304698924 hasConceptScore W4304698924C124101348 @default.
- W4304698924 hasConceptScore W4304698924C136886441 @default.
- W4304698924 hasConceptScore W4304698924C144024400 @default.
- W4304698924 hasConceptScore W4304698924C148730421 @default.
- W4304698924 hasConceptScore W4304698924C154945302 @default.
- W4304698924 hasConceptScore W4304698924C162984825 @default.
- W4304698924 hasConceptScore W4304698924C19165224 @default.
- W4304698924 hasConceptScore W4304698924C2779960059 @default.
- W4304698924 hasConceptScore W4304698924C38652104 @default.
- W4304698924 hasConceptScore W4304698924C40305131 @default.
- W4304698924 hasConceptScore W4304698924C41008148 @default.
- W4304698924 hasConceptScore W4304698924C50644808 @default.
- W4304698924 hasConceptScore W4304698924C73555534 @default.
- W4304698924 hasLocation W43046989241 @default.
- W4304698924 hasOpenAccess W4304698924 @default.
- W4304698924 hasPrimaryLocation W43046989241 @default.
- W4304698924 hasRelatedWork W1566685310 @default.
- W4304698924 hasRelatedWork W1664637288 @default.
- W4304698924 hasRelatedWork W1700031991 @default.
- W4304698924 hasRelatedWork W2130617689 @default.
- W4304698924 hasRelatedWork W2325250725 @default.
- W4304698924 hasRelatedWork W2381065783 @default.
- W4304698924 hasRelatedWork W2473769720 @default.
- W4304698924 hasRelatedWork W2526890902 @default.
- W4304698924 hasRelatedWork W2605786708 @default.
- W4304698924 hasRelatedWork W1629725936 @default.
- W4304698924 isParatext "false" @default.
- W4304698924 isRetracted "false" @default.
- W4304698924 workType "article" @default.