Why Train More? Effective and Efficient Membership Inference via Memorization Article Swipe
Jihye Choi
,
Shruti Tople
,
Varun Chandrasekaran
,
Somesh Jha
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.08015
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.08015
Membership Inference Attacks (MIAs) aim to identify specific data samples within the private training dataset of machine learning models, leading to serious privacy violations and other sophisticated threats. Many practical black-box MIAs require query access to the data distribution (the same distribution where the private data is drawn) to train shadow models. By doing so, the adversary obtains models trained "with" or "without" samples drawn from the distribution, and analyzes the characteristics of the samples under consideration. The adversary is often required to train more than hundreds of shadow models to extract the signals needed for MIAs; this becomes the computational overhead of MIAs. In this paper, we propose that by strategically choosing the samples, MI adversaries can maximize their attack success while minimizing the number of shadow models. First, our motivational experiments suggest memorization as the key property explaining disparate sample vulnerability to MIAs. We formalize this through a theoretical bound that connects MI advantage with memorization. Second, we show sample complexity bounds that connect the number of shadow models needed for MIAs with memorization. Lastly, we confirm our theoretical arguments with comprehensive experiments; by utilizing samples with high memorization scores, the adversary can (a) significantly improve its efficacy regardless of the MIA used, and (b) reduce the number of shadow models by nearly two orders of magnitude compared to state-of-the-art approaches.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2310.08015
- https://arxiv.org/pdf/2310.08015
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387635154
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387635154Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2310.08015Digital Object Identifier
- Title
-
Why Train More? Effective and Efficient Membership Inference via MemorizationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-10-12Full publication date if available
- Authors
-
Jihye Choi, Shruti Tople, Varun Chandrasekaran, Somesh JhaList of authors in order
- Landing page
-
https://arxiv.org/abs/2310.08015Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2310.08015Direct 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/2310.08015Direct OA link when available
- Concepts
-
Memorization, Adversary, Shadow (psychology), Computer science, Inference, Sample (material), Overhead (engineering), Artificial intelligence, Vulnerability (computing), Machine learning, Computer security, Mathematics, Psychology, Chemistry, Mathematics education, Chromatography, Operating system, PsychotherapistTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4387635154 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2310.08015 |
| ids.doi | https://doi.org/10.48550/arxiv.2310.08015 |
| ids.openalex | https://openalex.org/W4387635154 |
| fwci | |
| type | preprint |
| title | Why Train More? Effective and Efficient Membership Inference via Memorization |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11689 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9997000098228455 |
| 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 | Adversarial Robustness in Machine Learning |
| topics[1].id | https://openalex.org/T10764 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9815999865531921 |
| 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 | Privacy-Preserving Technologies in Data |
| topics[2].id | https://openalex.org/T11512 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9449999928474426 |
| 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 | Anomaly Detection Techniques and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C30038468 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8773866891860962 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q4354775 |
| concepts[0].display_name | Memorization |
| concepts[1].id | https://openalex.org/C41065033 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7690048813819885 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2825412 |
| concepts[1].display_name | Adversary |
| concepts[2].id | https://openalex.org/C117797892 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7440487146377563 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q286363 |
| concepts[2].display_name | Shadow (psychology) |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.7002820372581482 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C2776214188 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6328582167625427 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[4].display_name | Inference |
| concepts[5].id | https://openalex.org/C198531522 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5983282327651978 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q485146 |
| concepts[5].display_name | Sample (material) |
| concepts[6].id | https://openalex.org/C2779960059 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5728338360786438 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7113681 |
| concepts[6].display_name | Overhead (engineering) |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.4753662943840027 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C95713431 |
| concepts[8].level | 2 |
| concepts[8].score | 0.46431729197502136 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q631425 |
| concepts[8].display_name | Vulnerability (computing) |
| concepts[9].id | https://openalex.org/C119857082 |
| concepts[9].level | 1 |
| concepts[9].score | 0.4400354325771332 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[9].display_name | Machine learning |
| concepts[10].id | https://openalex.org/C38652104 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3003925085067749 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[10].display_name | Computer security |
| concepts[11].id | https://openalex.org/C33923547 |
| concepts[11].level | 0 |
| concepts[11].score | 0.18029624223709106 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[11].display_name | Mathematics |
| concepts[12].id | https://openalex.org/C15744967 |
| concepts[12].level | 0 |
| concepts[12].score | 0.070580393075943 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[12].display_name | Psychology |
| concepts[13].id | https://openalex.org/C185592680 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[13].display_name | Chemistry |
| concepts[14].id | https://openalex.org/C145420912 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q853077 |
| concepts[14].display_name | Mathematics education |
| concepts[15].id | https://openalex.org/C43617362 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q170050 |
| concepts[15].display_name | Chromatography |
| concepts[16].id | https://openalex.org/C111919701 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[16].display_name | Operating system |
| concepts[17].id | https://openalex.org/C542102704 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q183257 |
| concepts[17].display_name | Psychotherapist |
| keywords[0].id | https://openalex.org/keywords/memorization |
| keywords[0].score | 0.8773866891860962 |
| keywords[0].display_name | Memorization |
| keywords[1].id | https://openalex.org/keywords/adversary |
| keywords[1].score | 0.7690048813819885 |
| keywords[1].display_name | Adversary |
| keywords[2].id | https://openalex.org/keywords/shadow |
| keywords[2].score | 0.7440487146377563 |
| keywords[2].display_name | Shadow (psychology) |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.7002820372581482 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/inference |
| keywords[4].score | 0.6328582167625427 |
| keywords[4].display_name | Inference |
| keywords[5].id | https://openalex.org/keywords/sample |
| keywords[5].score | 0.5983282327651978 |
| keywords[5].display_name | Sample (material) |
| keywords[6].id | https://openalex.org/keywords/overhead |
| keywords[6].score | 0.5728338360786438 |
| keywords[6].display_name | Overhead (engineering) |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.4753662943840027 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/vulnerability |
| keywords[8].score | 0.46431729197502136 |
| keywords[8].display_name | Vulnerability (computing) |
| keywords[9].id | https://openalex.org/keywords/machine-learning |
| keywords[9].score | 0.4400354325771332 |
| keywords[9].display_name | Machine learning |
| keywords[10].id | https://openalex.org/keywords/computer-security |
| keywords[10].score | 0.3003925085067749 |
| keywords[10].display_name | Computer security |
| keywords[11].id | https://openalex.org/keywords/mathematics |
| keywords[11].score | 0.18029624223709106 |
| keywords[11].display_name | Mathematics |
| keywords[12].id | https://openalex.org/keywords/psychology |
| keywords[12].score | 0.070580393075943 |
| keywords[12].display_name | Psychology |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2310.08015 |
| 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/2310.08015 |
| 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/2310.08015 |
| locations[1].id | doi:10.48550/arxiv.2310.08015 |
| 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.2310.08015 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101725648 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7054-0289 |
| authorships[0].author.display_name | Jihye Choi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Choi, Jihye |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5076686201 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Shruti Tople |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Tople, Shruti |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5009092703 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-0661-6378 |
| authorships[2].author.display_name | Varun Chandrasekaran |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Chandrasekaran, Varun |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5088826068 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-5877-0436 |
| authorships[3].author.display_name | Somesh Jha |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Jha, Somesh |
| authorships[3].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/2310.08015 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Why Train More? Effective and Efficient Membership Inference via Memorization |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11689 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9997000098228455 |
| 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 | Adversarial Robustness in Machine Learning |
| related_works | https://openalex.org/W3163481960, https://openalex.org/W3093895509, https://openalex.org/W2323394100, https://openalex.org/W280704926, https://openalex.org/W2476068070, https://openalex.org/W4323971310, https://openalex.org/W2893372175, https://openalex.org/W1972827106, https://openalex.org/W4283526844, https://openalex.org/W2787003449 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2310.08015 |
| 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/2310.08015 |
| 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/2310.08015 |
| primary_location.id | pmh:oai:arXiv.org:2310.08015 |
| 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/2310.08015 |
| 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/2310.08015 |
| publication_date | 2023-10-12 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 149 |
| abstract_inverted_index.By | 52 |
| abstract_inverted_index.In | 104 |
| abstract_inverted_index.MI | 115, 154 |
| abstract_inverted_index.We | 145 |
| abstract_inverted_index.as | 135 |
| abstract_inverted_index.by | 110, 185, 213 |
| abstract_inverted_index.is | 46, 79 |
| abstract_inverted_index.of | 15, 72, 87, 102, 126, 168, 201, 210, 217 |
| abstract_inverted_index.or | 61 |
| abstract_inverted_index.to | 5, 20, 35, 48, 82, 90, 143, 220 |
| abstract_inverted_index.we | 107, 159, 177 |
| abstract_inverted_index.(a) | 195 |
| abstract_inverted_index.(b) | 206 |
| abstract_inverted_index.MIA | 203 |
| abstract_inverted_index.The | 77 |
| abstract_inverted_index.aim | 4 |
| abstract_inverted_index.and | 24, 68, 205 |
| abstract_inverted_index.can | 117, 194 |
| abstract_inverted_index.for | 95, 172 |
| abstract_inverted_index.its | 198 |
| abstract_inverted_index.key | 137 |
| abstract_inverted_index.our | 130, 179 |
| abstract_inverted_index.so, | 54 |
| abstract_inverted_index.the | 11, 36, 43, 55, 66, 70, 73, 92, 99, 113, 124, 136, 166, 192, 202, 208 |
| abstract_inverted_index.two | 215 |
| abstract_inverted_index.(the | 39 |
| abstract_inverted_index.MIAs | 31, 173 |
| abstract_inverted_index.Many | 28 |
| abstract_inverted_index.data | 8, 37, 45 |
| abstract_inverted_index.from | 65 |
| abstract_inverted_index.high | 189 |
| abstract_inverted_index.more | 84 |
| abstract_inverted_index.same | 40 |
| abstract_inverted_index.show | 160 |
| abstract_inverted_index.than | 85 |
| abstract_inverted_index.that | 109, 152, 164 |
| abstract_inverted_index.this | 97, 105, 147 |
| abstract_inverted_index.with | 156, 174, 182, 188 |
| abstract_inverted_index.MIAs. | 103, 144 |
| abstract_inverted_index.MIAs; | 96 |
| abstract_inverted_index.bound | 151 |
| abstract_inverted_index.doing | 53 |
| abstract_inverted_index.drawn | 64 |
| abstract_inverted_index.often | 80 |
| abstract_inverted_index.other | 25 |
| abstract_inverted_index.query | 33 |
| abstract_inverted_index.their | 119 |
| abstract_inverted_index.train | 49, 83 |
| abstract_inverted_index.under | 75 |
| abstract_inverted_index.used, | 204 |
| abstract_inverted_index.where | 42 |
| abstract_inverted_index.while | 122 |
| abstract_inverted_index."with" | 60 |
| abstract_inverted_index.(MIAs) | 3 |
| abstract_inverted_index.First, | 129 |
| abstract_inverted_index.access | 34 |
| abstract_inverted_index.attack | 120 |
| abstract_inverted_index.bounds | 163 |
| abstract_inverted_index.drawn) | 47 |
| abstract_inverted_index.models | 58, 89, 170, 212 |
| abstract_inverted_index.nearly | 214 |
| abstract_inverted_index.needed | 94, 171 |
| abstract_inverted_index.number | 125, 167, 209 |
| abstract_inverted_index.orders | 216 |
| abstract_inverted_index.paper, | 106 |
| abstract_inverted_index.reduce | 207 |
| abstract_inverted_index.sample | 141, 161 |
| abstract_inverted_index.shadow | 50, 88, 127, 169, 211 |
| abstract_inverted_index.within | 10 |
| abstract_inverted_index.Attacks | 2 |
| abstract_inverted_index.Lastly, | 176 |
| abstract_inverted_index.Second, | 158 |
| abstract_inverted_index.becomes | 98 |
| abstract_inverted_index.confirm | 178 |
| abstract_inverted_index.connect | 165 |
| abstract_inverted_index.dataset | 14 |
| abstract_inverted_index.extract | 91 |
| abstract_inverted_index.improve | 197 |
| abstract_inverted_index.leading | 19 |
| abstract_inverted_index.machine | 16 |
| abstract_inverted_index.models, | 18 |
| abstract_inverted_index.models. | 51, 128 |
| abstract_inverted_index.obtains | 57 |
| abstract_inverted_index.privacy | 22 |
| abstract_inverted_index.private | 12, 44 |
| abstract_inverted_index.propose | 108 |
| abstract_inverted_index.require | 32 |
| abstract_inverted_index.samples | 9, 63, 74, 187 |
| abstract_inverted_index.scores, | 191 |
| abstract_inverted_index.serious | 21 |
| abstract_inverted_index.signals | 93 |
| abstract_inverted_index.success | 121 |
| abstract_inverted_index.suggest | 133 |
| abstract_inverted_index.through | 148 |
| abstract_inverted_index.trained | 59 |
| abstract_inverted_index.analyzes | 69 |
| abstract_inverted_index.choosing | 112 |
| abstract_inverted_index.compared | 219 |
| abstract_inverted_index.connects | 153 |
| abstract_inverted_index.efficacy | 199 |
| abstract_inverted_index.hundreds | 86 |
| abstract_inverted_index.identify | 6 |
| abstract_inverted_index.learning | 17 |
| abstract_inverted_index.maximize | 118 |
| abstract_inverted_index.overhead | 101 |
| abstract_inverted_index.property | 138 |
| abstract_inverted_index.required | 81 |
| abstract_inverted_index.samples, | 114 |
| abstract_inverted_index.specific | 7 |
| abstract_inverted_index.threats. | 27 |
| abstract_inverted_index.training | 13 |
| abstract_inverted_index."without" | 62 |
| abstract_inverted_index.Inference | 1 |
| abstract_inverted_index.advantage | 155 |
| abstract_inverted_index.adversary | 56, 78, 193 |
| abstract_inverted_index.arguments | 181 |
| abstract_inverted_index.black-box | 30 |
| abstract_inverted_index.disparate | 140 |
| abstract_inverted_index.formalize | 146 |
| abstract_inverted_index.magnitude | 218 |
| abstract_inverted_index.practical | 29 |
| abstract_inverted_index.utilizing | 186 |
| abstract_inverted_index.Membership | 0 |
| abstract_inverted_index.complexity | 162 |
| abstract_inverted_index.explaining | 139 |
| abstract_inverted_index.minimizing | 123 |
| abstract_inverted_index.regardless | 200 |
| abstract_inverted_index.violations | 23 |
| abstract_inverted_index.adversaries | 116 |
| abstract_inverted_index.approaches. | 222 |
| abstract_inverted_index.experiments | 132 |
| abstract_inverted_index.theoretical | 150, 180 |
| abstract_inverted_index.distribution | 38, 41 |
| abstract_inverted_index.experiments; | 184 |
| abstract_inverted_index.memorization | 134, 190 |
| abstract_inverted_index.motivational | 131 |
| abstract_inverted_index.comprehensive | 183 |
| abstract_inverted_index.computational | 100 |
| abstract_inverted_index.distribution, | 67 |
| abstract_inverted_index.memorization. | 157, 175 |
| abstract_inverted_index.significantly | 196 |
| abstract_inverted_index.sophisticated | 26 |
| abstract_inverted_index.strategically | 111 |
| abstract_inverted_index.vulnerability | 142 |
| abstract_inverted_index.consideration. | 76 |
| abstract_inverted_index.characteristics | 71 |
| abstract_inverted_index.state-of-the-art | 221 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.7200000286102295 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile |