Towards a Theoretical Understanding of the Robustness of Variational\n Autoencoders Article Swipe
Alexander Camuto
,
Matthew Willetts
,
Stephen Roberts
,
Chris Holmes
,
Tom Rainforth
·
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2007.07365
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2007.07365
We make inroads into understanding the robustness of Variational Autoencoders\n(VAEs) to adversarial attacks and other input perturbations. While previous\nwork has developed algorithmic approaches to attacking and defending VAEs,\nthere remains a lack of formalization for what it means for a VAE to be robust.\nTo address this, we develop a novel criterion for robustness in probabilistic\nmodels: $r$-robustness. We then use this to construct the first theoretical\nresults for the robustness of VAEs, deriving margins in the input space for\nwhich we can provide guarantees about the resulting reconstruction. Informally,\nwe are able to define a region within which any perturbation will produce a\nreconstruction that is similar to the original reconstruction. To support our\nanalysis, we show that VAEs trained using disentangling methods not only score\nwell under our robustness metrics, but that the reasons for this can be\ninterpreted through our theoretical results.\n
Related Topics
Concepts
Metadata
- Type
- preprint
- Landing Page
- http://arxiv.org/abs/2007.07365
- https://arxiv.org/pdf/2007.07365
- OA Status
- green
- Cited By
- 4
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4287723492
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4287723492Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2007.07365Digital Object Identifier
- Title
-
Towards a Theoretical Understanding of the Robustness of Variational\n AutoencodersWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2020Year of publication
- Publication date
-
2020-07-14Full publication date if available
- Authors
-
Alexander Camuto, Matthew Willetts, Stephen Roberts, Chris Holmes, Tom RainforthList of authors in order
- Landing page
-
https://arxiv.org/abs/2007.07365Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2007.07365Direct 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/2007.07365Direct OA link when available
- Concepts
-
Robustness (evolution), Computer science, Artificial intelligence, Probabilistic logic, Adversarial system, Machine learning, Algorithm, Chemistry, Biochemistry, GeneTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
4Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 3, 2021: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4287723492 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2007.07365 |
| ids.openalex | https://openalex.org/W4287723492 |
| fwci | 0.14685955 |
| type | preprint |
| title | Towards a Theoretical Understanding of the Robustness of Variational\n Autoencoders |
| 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 | 0.9994000196456909 |
| 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/T11515 |
| topics[1].field.id | https://openalex.org/fields/13 |
| topics[1].field.display_name | Biochemistry, Genetics and Molecular Biology |
| topics[1].score | 0.9391000270843506 |
| topics[1].domain.id | https://openalex.org/domains/1 |
| topics[1].domain.display_name | Life Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1312 |
| topics[1].subfield.display_name | Molecular Biology |
| topics[1].display_name | Bacillus and Francisella bacterial research |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C63479239 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8953808546066284 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[0].display_name | Robustness (evolution) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6897484064102173 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5402163863182068 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C49937458 |
| concepts[3].level | 2 |
| concepts[3].score | 0.47828230261802673 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2599292 |
| concepts[3].display_name | Probabilistic logic |
| concepts[4].id | https://openalex.org/C37736160 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4707522988319397 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[4].display_name | Adversarial system |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.4338383376598358 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C11413529 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3357950448989868 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[6].display_name | Algorithm |
| concepts[7].id | https://openalex.org/C185592680 |
| concepts[7].level | 0 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[7].display_name | Chemistry |
| concepts[8].id | https://openalex.org/C55493867 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[8].display_name | Biochemistry |
| concepts[9].id | https://openalex.org/C104317684 |
| concepts[9].level | 2 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[9].display_name | Gene |
| keywords[0].id | https://openalex.org/keywords/robustness |
| keywords[0].score | 0.8953808546066284 |
| keywords[0].display_name | Robustness (evolution) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6897484064102173 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.5402163863182068 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/probabilistic-logic |
| keywords[3].score | 0.47828230261802673 |
| keywords[3].display_name | Probabilistic logic |
| keywords[4].id | https://openalex.org/keywords/adversarial-system |
| keywords[4].score | 0.4707522988319397 |
| keywords[4].display_name | Adversarial system |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.4338383376598358 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/algorithm |
| keywords[6].score | 0.3357950448989868 |
| keywords[6].display_name | Algorithm |
| language | |
| locations[0].id | pmh:oai:arXiv.org:2007.07365 |
| 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/2007.07365 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| 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/2007.07365 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5075596560 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Alexander Camuto |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Camuto, Alexander |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5019067441 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6585-3950 |
| authorships[1].author.display_name | Matthew Willetts |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Willetts, Matthew |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5058617210 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-9305-9268 |
| authorships[2].author.display_name | Stephen Roberts |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Roberts, Stephen |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100649922 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-6667-4943 |
| authorships[3].author.display_name | Chris Holmes |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Holmes, Chris |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5078631467 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Tom Rainforth |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Rainforth, Tom |
| authorships[4].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/2007.07365 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-07-26T00:00:00 |
| display_name | Towards a Theoretical Understanding of the Robustness of Variational\n Autoencoders |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9994000196456909 |
| 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/W2502115930, https://openalex.org/W2482350142, https://openalex.org/W4246396837, https://openalex.org/W3126451824, https://openalex.org/W1561927205, https://openalex.org/W3191453585, https://openalex.org/W4297672492, https://openalex.org/W4288019534, https://openalex.org/W4310988119, https://openalex.org/W4285226279 |
| cited_by_count | 4 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 3 |
| counts_by_year[1].year | 2021 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2007.07365 |
| 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/2007.07365 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| 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/2007.07365 |
| primary_location.id | pmh:oai:arXiv.org:2007.07365 |
| 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/2007.07365 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| 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/2007.07365 |
| publication_date | 2020-07-14 |
| publication_year | 2020 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 29, 38, 47, 89 |
| abstract_inverted_index.To | 105 |
| abstract_inverted_index.We | 0, 55 |
| abstract_inverted_index.be | 41 |
| abstract_inverted_index.in | 52, 71 |
| abstract_inverted_index.is | 99 |
| abstract_inverted_index.it | 35 |
| abstract_inverted_index.of | 7, 31, 67 |
| abstract_inverted_index.to | 10, 23, 40, 59, 87, 101 |
| abstract_inverted_index.we | 45, 76, 108 |
| abstract_inverted_index.VAE | 39 |
| abstract_inverted_index.and | 13, 25 |
| abstract_inverted_index.any | 93 |
| abstract_inverted_index.are | 85 |
| abstract_inverted_index.but | 123 |
| abstract_inverted_index.can | 77, 129 |
| abstract_inverted_index.for | 33, 37, 50, 64, 127 |
| abstract_inverted_index.has | 19 |
| abstract_inverted_index.not | 116 |
| abstract_inverted_index.our | 120, 132 |
| abstract_inverted_index.the | 5, 61, 65, 72, 81, 102, 125 |
| abstract_inverted_index.use | 57 |
| abstract_inverted_index.VAEs | 111 |
| abstract_inverted_index.able | 86 |
| abstract_inverted_index.into | 3 |
| abstract_inverted_index.lack | 30 |
| abstract_inverted_index.make | 1 |
| abstract_inverted_index.only | 117 |
| abstract_inverted_index.show | 109 |
| abstract_inverted_index.that | 98, 110, 124 |
| abstract_inverted_index.then | 56 |
| abstract_inverted_index.this | 58, 128 |
| abstract_inverted_index.what | 34 |
| abstract_inverted_index.will | 95 |
| abstract_inverted_index.VAEs, | 68 |
| abstract_inverted_index.While | 17 |
| abstract_inverted_index.about | 80 |
| abstract_inverted_index.first | 62 |
| abstract_inverted_index.input | 15, 73 |
| abstract_inverted_index.means | 36 |
| abstract_inverted_index.novel | 48 |
| abstract_inverted_index.other | 14 |
| abstract_inverted_index.space | 74 |
| abstract_inverted_index.this, | 44 |
| abstract_inverted_index.under | 119 |
| abstract_inverted_index.using | 113 |
| abstract_inverted_index.which | 92 |
| abstract_inverted_index.define | 88 |
| abstract_inverted_index.region | 90 |
| abstract_inverted_index.within | 91 |
| abstract_inverted_index.address | 43 |
| abstract_inverted_index.attacks | 12 |
| abstract_inverted_index.develop | 46 |
| abstract_inverted_index.inroads | 2 |
| abstract_inverted_index.margins | 70 |
| abstract_inverted_index.methods | 115 |
| abstract_inverted_index.produce | 96 |
| abstract_inverted_index.provide | 78 |
| abstract_inverted_index.reasons | 126 |
| abstract_inverted_index.remains | 28 |
| abstract_inverted_index.similar | 100 |
| abstract_inverted_index.support | 106 |
| abstract_inverted_index.through | 131 |
| abstract_inverted_index.trained | 112 |
| abstract_inverted_index.deriving | 69 |
| abstract_inverted_index.metrics, | 122 |
| abstract_inverted_index.original | 103 |
| abstract_inverted_index.attacking | 24 |
| abstract_inverted_index.construct | 60 |
| abstract_inverted_index.criterion | 49 |
| abstract_inverted_index.defending | 26 |
| abstract_inverted_index.developed | 20 |
| abstract_inverted_index.resulting | 82 |
| abstract_inverted_index.approaches | 22 |
| abstract_inverted_index.for\nwhich | 75 |
| abstract_inverted_index.guarantees | 79 |
| abstract_inverted_index.results.\n | 134 |
| abstract_inverted_index.robustness | 6, 51, 66, 121 |
| abstract_inverted_index.Variational | 8 |
| abstract_inverted_index.adversarial | 11 |
| abstract_inverted_index.algorithmic | 21 |
| abstract_inverted_index.robust.\nTo | 42 |
| abstract_inverted_index.score\nwell | 118 |
| abstract_inverted_index.theoretical | 133 |
| abstract_inverted_index.VAEs,\nthere | 27 |
| abstract_inverted_index.perturbation | 94 |
| abstract_inverted_index.disentangling | 114 |
| abstract_inverted_index.formalization | 32 |
| abstract_inverted_index.understanding | 4 |
| abstract_inverted_index.our\nanalysis, | 107 |
| abstract_inverted_index.perturbations. | 16 |
| abstract_inverted_index.previous\nwork | 18 |
| abstract_inverted_index.$r$-robustness. | 54 |
| abstract_inverted_index.Informally,\nwe | 84 |
| abstract_inverted_index.be\ninterpreted | 130 |
| abstract_inverted_index.reconstruction. | 83, 104 |
| abstract_inverted_index.a\nreconstruction | 97 |
| abstract_inverted_index.Autoencoders\n(VAEs) | 9 |
| abstract_inverted_index.theoretical\nresults | 63 |
| abstract_inverted_index.probabilistic\nmodels: | 53 |
| cited_by_percentile_year.max | 97 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/10 |
| sustainable_development_goals[0].score | 0.5400000214576721 |
| sustainable_development_goals[0].display_name | Reduced inequalities |
| citation_normalized_percentile.value | 0.60744834 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |