On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation Article Swipe
Yucong Liu
,
Chi-Hua Wang
,
Guang Cheng
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2211.15809
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2211.15809
Devising procedures for auditing generative model privacy-utility tradeoff is an important yet unresolved problem in practice. Existing works concentrates on investigating the privacy constraint side effect in terms of utility degradation of the train on synthetic, test on real paradigm of synthetic data training. We push such understanding on privacy-utility tradeoff to next level by observing the privacy deregulation side effect on synthetic training data utility. Surprisingly, we discover the Utility Recovery Incapability of DP-CTGAN and PATE-CTGAN under privacy deregulation, raising concerns on their practical applications. The main message is Privacy Deregulation does NOT always imply Utility Recovery.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2211.15809
- https://arxiv.org/pdf/2211.15809
- OA Status
- green
- Cited By
- 3
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4310510015
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4310510015Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2211.15809Digital Object Identifier
- Title
-
On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy DeregulationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-11-28Full publication date if available
- Authors
-
Yucong Liu, Chi-Hua Wang, Guang ChengList of authors in order
- Landing page
-
https://arxiv.org/abs/2211.15809Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2211.15809Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2211.15809Direct OA link when available
- Concepts
-
Deregulation, Differential privacy, Computer science, Constraint (computer-aided design), Audit, Generative model, Computer security, Generative grammar, Artificial intelligence, Business, Data mining, Economics, Engineering, Accounting, Mechanical engineering, MacroeconomicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
3Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 2, 2023: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4310510015 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2211.15809 |
| ids.doi | https://doi.org/10.48550/arxiv.2211.15809 |
| ids.openalex | https://openalex.org/W4310510015 |
| fwci | |
| type | preprint |
| title | On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10764 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9975000023841858 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Privacy-Preserving Technologies in Data |
| topics[1].id | https://openalex.org/T11612 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9861999750137329 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Stochastic Gradient Optimization Techniques |
| topics[2].id | https://openalex.org/T10237 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9666000008583069 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Cryptography and Data Security |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C78780426 |
| concepts[0].level | 2 |
| concepts[0].score | 0.861701488494873 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q902410 |
| concepts[0].display_name | Deregulation |
| concepts[1].id | https://openalex.org/C23130292 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7726618051528931 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q5275358 |
| concepts[1].display_name | Differential privacy |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6493087410926819 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C2776036281 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5668188333511353 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q48769818 |
| concepts[3].display_name | Constraint (computer-aided design) |
| concepts[4].id | https://openalex.org/C199521495 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5351133942604065 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q181487 |
| concepts[4].display_name | Audit |
| concepts[5].id | https://openalex.org/C167966045 |
| concepts[5].level | 3 |
| concepts[5].score | 0.5086013078689575 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q5532625 |
| concepts[5].display_name | Generative model |
| concepts[6].id | https://openalex.org/C38652104 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3642041087150574 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[6].display_name | Computer security |
| concepts[7].id | https://openalex.org/C39890363 |
| concepts[7].level | 2 |
| concepts[7].score | 0.3169761896133423 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q36108 |
| concepts[7].display_name | Generative grammar |
| concepts[8].id | https://openalex.org/C154945302 |
| concepts[8].level | 1 |
| concepts[8].score | 0.3113342523574829 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[8].display_name | Artificial intelligence |
| concepts[9].id | https://openalex.org/C144133560 |
| concepts[9].level | 0 |
| concepts[9].score | 0.23963525891304016 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q4830453 |
| concepts[9].display_name | Business |
| concepts[10].id | https://openalex.org/C124101348 |
| concepts[10].level | 1 |
| concepts[10].score | 0.16612547636032104 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q172491 |
| concepts[10].display_name | Data mining |
| concepts[11].id | https://openalex.org/C162324750 |
| concepts[11].level | 0 |
| concepts[11].score | 0.14656886458396912 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[11].display_name | Economics |
| concepts[12].id | https://openalex.org/C127413603 |
| concepts[12].level | 0 |
| concepts[12].score | 0.11015325784683228 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[12].display_name | Engineering |
| concepts[13].id | https://openalex.org/C121955636 |
| concepts[13].level | 1 |
| concepts[13].score | 0.07033836841583252 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q4116214 |
| concepts[13].display_name | Accounting |
| concepts[14].id | https://openalex.org/C78519656 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q101333 |
| concepts[14].display_name | Mechanical engineering |
| concepts[15].id | https://openalex.org/C139719470 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q39680 |
| concepts[15].display_name | Macroeconomics |
| keywords[0].id | https://openalex.org/keywords/deregulation |
| keywords[0].score | 0.861701488494873 |
| keywords[0].display_name | Deregulation |
| keywords[1].id | https://openalex.org/keywords/differential-privacy |
| keywords[1].score | 0.7726618051528931 |
| keywords[1].display_name | Differential privacy |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6493087410926819 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/constraint |
| keywords[3].score | 0.5668188333511353 |
| keywords[3].display_name | Constraint (computer-aided design) |
| keywords[4].id | https://openalex.org/keywords/audit |
| keywords[4].score | 0.5351133942604065 |
| keywords[4].display_name | Audit |
| keywords[5].id | https://openalex.org/keywords/generative-model |
| keywords[5].score | 0.5086013078689575 |
| keywords[5].display_name | Generative model |
| keywords[6].id | https://openalex.org/keywords/computer-security |
| keywords[6].score | 0.3642041087150574 |
| keywords[6].display_name | Computer security |
| keywords[7].id | https://openalex.org/keywords/generative-grammar |
| keywords[7].score | 0.3169761896133423 |
| keywords[7].display_name | Generative grammar |
| keywords[8].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[8].score | 0.3113342523574829 |
| keywords[8].display_name | Artificial intelligence |
| keywords[9].id | https://openalex.org/keywords/business |
| keywords[9].score | 0.23963525891304016 |
| keywords[9].display_name | Business |
| keywords[10].id | https://openalex.org/keywords/data-mining |
| keywords[10].score | 0.16612547636032104 |
| keywords[10].display_name | Data mining |
| keywords[11].id | https://openalex.org/keywords/economics |
| keywords[11].score | 0.14656886458396912 |
| keywords[11].display_name | Economics |
| keywords[12].id | https://openalex.org/keywords/engineering |
| keywords[12].score | 0.11015325784683228 |
| keywords[12].display_name | Engineering |
| keywords[13].id | https://openalex.org/keywords/accounting |
| keywords[13].score | 0.07033836841583252 |
| keywords[13].display_name | Accounting |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2211.15809 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2211.15809 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2211.15809 |
| locations[1].id | doi:10.48550/arxiv.2211.15809 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2211.15809 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5025152292 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-3753-9670 |
| authorships[0].author.display_name | Yucong Liu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Liu, Yucong |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5009384065 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Chi-Hua Wang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wang, Chi-Hua |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101688179 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-7874-9404 |
| authorships[2].author.display_name | Guang Cheng |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Cheng, Guang |
| authorships[2].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2211.15809 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-12-11T00:00:00 |
| display_name | On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10764 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9975000023841858 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Privacy-Preserving Technologies in Data |
| related_works | https://openalex.org/W4365211920, https://openalex.org/W3014948380, https://openalex.org/W4380551139, https://openalex.org/W4317695495, https://openalex.org/W4287117424, https://openalex.org/W4387506531, https://openalex.org/W4238433571, https://openalex.org/W3174044702, https://openalex.org/W2967848559, https://openalex.org/W4299831724 |
| cited_by_count | 3 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2211.15809 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2211.15809 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2211.15809 |
| primary_location.id | pmh:oai:arXiv.org:2211.15809 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2211.15809 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2211.15809 |
| publication_date | 2022-11-28 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.We | 44 |
| abstract_inverted_index.an | 9 |
| abstract_inverted_index.by | 54 |
| abstract_inverted_index.in | 14, 26 |
| abstract_inverted_index.is | 8, 89 |
| abstract_inverted_index.of | 28, 31, 40, 73 |
| abstract_inverted_index.on | 19, 34, 37, 48, 61, 82 |
| abstract_inverted_index.to | 51 |
| abstract_inverted_index.we | 67 |
| abstract_inverted_index.NOT | 93 |
| abstract_inverted_index.The | 86 |
| abstract_inverted_index.and | 75 |
| abstract_inverted_index.for | 2 |
| abstract_inverted_index.the | 21, 32, 56, 69 |
| abstract_inverted_index.yet | 11 |
| abstract_inverted_index.data | 42, 64 |
| abstract_inverted_index.does | 92 |
| abstract_inverted_index.main | 87 |
| abstract_inverted_index.next | 52 |
| abstract_inverted_index.push | 45 |
| abstract_inverted_index.real | 38 |
| abstract_inverted_index.side | 24, 59 |
| abstract_inverted_index.such | 46 |
| abstract_inverted_index.test | 36 |
| abstract_inverted_index.imply | 95 |
| abstract_inverted_index.level | 53 |
| abstract_inverted_index.model | 5 |
| abstract_inverted_index.terms | 27 |
| abstract_inverted_index.their | 83 |
| abstract_inverted_index.train | 33 |
| abstract_inverted_index.under | 77 |
| abstract_inverted_index.works | 17 |
| abstract_inverted_index.always | 94 |
| abstract_inverted_index.effect | 25, 60 |
| abstract_inverted_index.Privacy | 90 |
| abstract_inverted_index.Utility | 70, 96 |
| abstract_inverted_index.message | 88 |
| abstract_inverted_index.privacy | 22, 57, 78 |
| abstract_inverted_index.problem | 13 |
| abstract_inverted_index.raising | 80 |
| abstract_inverted_index.utility | 29 |
| abstract_inverted_index.DP-CTGAN | 74 |
| abstract_inverted_index.Devising | 0 |
| abstract_inverted_index.Existing | 16 |
| abstract_inverted_index.Recovery | 71 |
| abstract_inverted_index.auditing | 3 |
| abstract_inverted_index.concerns | 81 |
| abstract_inverted_index.discover | 68 |
| abstract_inverted_index.paradigm | 39 |
| abstract_inverted_index.tradeoff | 7, 50 |
| abstract_inverted_index.training | 63 |
| abstract_inverted_index.utility. | 65 |
| abstract_inverted_index.Recovery. | 97 |
| abstract_inverted_index.important | 10 |
| abstract_inverted_index.observing | 55 |
| abstract_inverted_index.practical | 84 |
| abstract_inverted_index.practice. | 15 |
| abstract_inverted_index.synthetic | 41, 62 |
| abstract_inverted_index.training. | 43 |
| abstract_inverted_index.PATE-CTGAN | 76 |
| abstract_inverted_index.constraint | 23 |
| abstract_inverted_index.generative | 4 |
| abstract_inverted_index.procedures | 1 |
| abstract_inverted_index.synthetic, | 35 |
| abstract_inverted_index.unresolved | 12 |
| abstract_inverted_index.degradation | 30 |
| abstract_inverted_index.Deregulation | 91 |
| abstract_inverted_index.Incapability | 72 |
| abstract_inverted_index.concentrates | 18 |
| abstract_inverted_index.deregulation | 58 |
| abstract_inverted_index.Surprisingly, | 66 |
| abstract_inverted_index.applications. | 85 |
| abstract_inverted_index.deregulation, | 79 |
| abstract_inverted_index.investigating | 20 |
| abstract_inverted_index.understanding | 47 |
| abstract_inverted_index.privacy-utility | 6, 49 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.47999998927116394 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile |