Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches Article Swipe
Aniruddha Saha
,
Shuhua Yu
,
Arash Norouzzadeh
,
Wan-Yi Lin
,
Chaithanya Kumar Mummadi
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2306.12610
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2306.12610
Certifiably robust defenses against adversarial patches for image classifiers ensure correct prediction against any changes to a constrained neighborhood of pixels. PatchCleanser arXiv:2108.09135 [cs.CV], the state-of-the-art certified defense, uses a double-masking strategy for robust classification. The success of this strategy relies heavily on the model's invariance to image pixel masking. In this paper, we take a closer look at model training schemes to improve this invariance. Instead of using Random Cutout arXiv:1708.04552v2 [cs.CV] augmentations like PatchCleanser, we introduce the notion of worst-case masking, i.e., selecting masked images which maximize classification loss. However, finding worst-case masks requires an exhaustive search, which might be prohibitively expensive to do on-the-fly during training. To solve this problem, we propose a two-round greedy masking strategy (Greedy Cutout) which finds an approximate worst-case mask location with much less compute. We show that the models trained with our Greedy Cutout improves certified robust accuracy over Random Cutout in PatchCleanser across a range of datasets and architectures. Certified robust accuracy on ImageNet with a ViT-B16-224 model increases from 58.1\% to 62.3\% against a 3\% square patch applied anywhere on the image.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2306.12610
- https://arxiv.org/pdf/2306.12610
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4381826952
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4381826952Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2306.12610Digital Object Identifier
- Title
-
Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial PatchesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-06-22Full publication date if available
- Authors
-
Aniruddha Saha, Shuhua Yu, Arash Norouzzadeh, Wan-Yi Lin, Chaithanya Kumar MummadiList of authors in order
- Landing page
-
https://arxiv.org/abs/2306.12610Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2306.12610Direct 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/2306.12610Direct OA link when available
- Concepts
-
Computer science, Certification, Adversarial system, Artificial intelligence, Pixel, Masking (illustration), Classifier (UML), Image (mathematics), Training set, Greedy algorithm, Machine learning, Pattern recognition (psychology), Algorithm, Political science, Law, Art, Visual artsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4381826952 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2306.12610 |
| ids.doi | https://doi.org/10.48550/arxiv.2306.12610 |
| ids.openalex | https://openalex.org/W4381826952 |
| fwci | |
| type | preprint |
| title | Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches |
| 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 | 0.9998000264167786 |
| 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/T11512 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9602000117301941 |
| 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 | Anomaly Detection Techniques and Applications |
| topics[2].id | https://openalex.org/T11515 |
| topics[2].field.id | https://openalex.org/fields/13 |
| topics[2].field.display_name | Biochemistry, Genetics and Molecular Biology |
| topics[2].score | 0.9171000123023987 |
| topics[2].domain.id | https://openalex.org/domains/1 |
| topics[2].domain.display_name | Life Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1312 |
| topics[2].subfield.display_name | Molecular Biology |
| topics[2].display_name | Bacillus and Francisella bacterial research |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6644861102104187 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C46304622 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6475196480751038 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q374814 |
| concepts[1].display_name | Certification |
| concepts[2].id | https://openalex.org/C37736160 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6111668944358826 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[2].display_name | Adversarial system |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5916919112205505 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C160633673 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5789380669593811 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q355198 |
| concepts[4].display_name | Pixel |
| concepts[5].id | https://openalex.org/C2777402240 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5550697445869446 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q6783436 |
| concepts[5].display_name | Masking (illustration) |
| concepts[6].id | https://openalex.org/C95623464 |
| concepts[6].level | 2 |
| concepts[6].score | 0.504719614982605 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1096149 |
| concepts[6].display_name | Classifier (UML) |
| concepts[7].id | https://openalex.org/C115961682 |
| concepts[7].level | 2 |
| concepts[7].score | 0.49615105986595154 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[7].display_name | Image (mathematics) |
| concepts[8].id | https://openalex.org/C51632099 |
| concepts[8].level | 2 |
| concepts[8].score | 0.44351568818092346 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q3985153 |
| concepts[8].display_name | Training set |
| concepts[9].id | https://openalex.org/C51823790 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4383101463317871 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q504353 |
| concepts[9].display_name | Greedy algorithm |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.4259741008281708 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C153180895 |
| concepts[11].level | 2 |
| concepts[11].score | 0.4244269132614136 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[11].display_name | Pattern recognition (psychology) |
| concepts[12].id | https://openalex.org/C11413529 |
| concepts[12].level | 1 |
| concepts[12].score | 0.26304441690444946 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[12].display_name | Algorithm |
| concepts[13].id | https://openalex.org/C17744445 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[13].display_name | Political science |
| concepts[14].id | https://openalex.org/C199539241 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[14].display_name | Law |
| concepts[15].id | https://openalex.org/C142362112 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q735 |
| concepts[15].display_name | Art |
| concepts[16].id | https://openalex.org/C153349607 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q36649 |
| concepts[16].display_name | Visual arts |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6644861102104187 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/certification |
| keywords[1].score | 0.6475196480751038 |
| keywords[1].display_name | Certification |
| keywords[2].id | https://openalex.org/keywords/adversarial-system |
| keywords[2].score | 0.6111668944358826 |
| keywords[2].display_name | Adversarial system |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5916919112205505 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/pixel |
| keywords[4].score | 0.5789380669593811 |
| keywords[4].display_name | Pixel |
| keywords[5].id | https://openalex.org/keywords/masking |
| keywords[5].score | 0.5550697445869446 |
| keywords[5].display_name | Masking (illustration) |
| keywords[6].id | https://openalex.org/keywords/classifier |
| keywords[6].score | 0.504719614982605 |
| keywords[6].display_name | Classifier (UML) |
| keywords[7].id | https://openalex.org/keywords/image |
| keywords[7].score | 0.49615105986595154 |
| keywords[7].display_name | Image (mathematics) |
| keywords[8].id | https://openalex.org/keywords/training-set |
| keywords[8].score | 0.44351568818092346 |
| keywords[8].display_name | Training set |
| keywords[9].id | https://openalex.org/keywords/greedy-algorithm |
| keywords[9].score | 0.4383101463317871 |
| keywords[9].display_name | Greedy algorithm |
| keywords[10].id | https://openalex.org/keywords/machine-learning |
| keywords[10].score | 0.4259741008281708 |
| keywords[10].display_name | Machine learning |
| keywords[11].id | https://openalex.org/keywords/pattern-recognition |
| keywords[11].score | 0.4244269132614136 |
| keywords[11].display_name | Pattern recognition (psychology) |
| keywords[12].id | https://openalex.org/keywords/algorithm |
| keywords[12].score | 0.26304441690444946 |
| keywords[12].display_name | Algorithm |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2306.12610 |
| 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/2306.12610 |
| 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/2306.12610 |
| locations[1].id | doi:10.48550/arxiv.2306.12610 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2306.12610 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5110640669 |
| authorships[0].author.orcid | https://orcid.org/0009-0000-4532-7507 |
| authorships[0].author.display_name | Aniruddha Saha |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Saha, Aniruddha |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100528028 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Shuhua Yu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yu, Shuhua |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5032024307 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Arash Norouzzadeh |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Norouzzadeh, Arash |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5081093105 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Wan-Yi Lin |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Lin, Wan-Yi |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5077132380 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-1173-2720 |
| authorships[4].author.display_name | Chaithanya Kumar Mummadi |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Mummadi, Chaithanya Kumar |
| 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/2306.12610 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches |
| 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 | 0.9998000264167786 |
| 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/W3183948672, https://openalex.org/W3173606202, https://openalex.org/W3110381201, https://openalex.org/W2778153218, https://openalex.org/W1531601525, https://openalex.org/W3211393740, https://openalex.org/W3208049411, https://openalex.org/W3022908591, https://openalex.org/W4285706568, https://openalex.org/W2946768379 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2306.12610 |
| 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/2306.12610 |
| 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/2306.12610 |
| primary_location.id | pmh:oai:arXiv.org:2306.12610 |
| 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/2306.12610 |
| 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/2306.12610 |
| publication_date | 2023-06-22 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 16, 29, 55, 115, 153, 165, 174 |
| abstract_inverted_index.In | 50 |
| abstract_inverted_index.To | 109 |
| abstract_inverted_index.We | 133 |
| abstract_inverted_index.an | 96, 124 |
| abstract_inverted_index.at | 58 |
| abstract_inverted_index.be | 101 |
| abstract_inverted_index.do | 105 |
| abstract_inverted_index.in | 150 |
| abstract_inverted_index.of | 19, 37, 67, 80, 155 |
| abstract_inverted_index.on | 42, 162, 180 |
| abstract_inverted_index.to | 15, 46, 62, 104, 171 |
| abstract_inverted_index.we | 53, 76, 113 |
| abstract_inverted_index.3\% | 175 |
| abstract_inverted_index.The | 35 |
| abstract_inverted_index.and | 157 |
| abstract_inverted_index.any | 13 |
| abstract_inverted_index.for | 6, 32 |
| abstract_inverted_index.our | 140 |
| abstract_inverted_index.the | 24, 43, 78, 136, 181 |
| abstract_inverted_index.from | 169 |
| abstract_inverted_index.less | 131 |
| abstract_inverted_index.like | 74 |
| abstract_inverted_index.look | 57 |
| abstract_inverted_index.mask | 127 |
| abstract_inverted_index.much | 130 |
| abstract_inverted_index.over | 147 |
| abstract_inverted_index.show | 134 |
| abstract_inverted_index.take | 54 |
| abstract_inverted_index.that | 135 |
| abstract_inverted_index.this | 38, 51, 64, 111 |
| abstract_inverted_index.uses | 28 |
| abstract_inverted_index.with | 129, 139, 164 |
| abstract_inverted_index.finds | 123 |
| abstract_inverted_index.i.e., | 83 |
| abstract_inverted_index.image | 7, 47 |
| abstract_inverted_index.loss. | 90 |
| abstract_inverted_index.masks | 94 |
| abstract_inverted_index.might | 100 |
| abstract_inverted_index.model | 59, 167 |
| abstract_inverted_index.patch | 177 |
| abstract_inverted_index.pixel | 48 |
| abstract_inverted_index.range | 154 |
| abstract_inverted_index.solve | 110 |
| abstract_inverted_index.using | 68 |
| abstract_inverted_index.which | 87, 99, 122 |
| abstract_inverted_index.58.1\% | 170 |
| abstract_inverted_index.62.3\% | 172 |
| abstract_inverted_index.Cutout | 70, 142, 149 |
| abstract_inverted_index.Greedy | 141 |
| abstract_inverted_index.Random | 69, 148 |
| abstract_inverted_index.across | 152 |
| abstract_inverted_index.closer | 56 |
| abstract_inverted_index.during | 107 |
| abstract_inverted_index.ensure | 9 |
| abstract_inverted_index.greedy | 117 |
| abstract_inverted_index.image. | 182 |
| abstract_inverted_index.images | 86 |
| abstract_inverted_index.masked | 85 |
| abstract_inverted_index.models | 137 |
| abstract_inverted_index.notion | 79 |
| abstract_inverted_index.paper, | 52 |
| abstract_inverted_index.relies | 40 |
| abstract_inverted_index.robust | 1, 33, 145, 160 |
| abstract_inverted_index.square | 176 |
| abstract_inverted_index.(Greedy | 120 |
| abstract_inverted_index.Cutout) | 121 |
| abstract_inverted_index.Instead | 66 |
| abstract_inverted_index.[cs.CV] | 72 |
| abstract_inverted_index.against | 3, 12, 173 |
| abstract_inverted_index.applied | 178 |
| abstract_inverted_index.changes | 14 |
| abstract_inverted_index.correct | 10 |
| abstract_inverted_index.finding | 92 |
| abstract_inverted_index.heavily | 41 |
| abstract_inverted_index.improve | 63 |
| abstract_inverted_index.masking | 118 |
| abstract_inverted_index.model's | 44 |
| abstract_inverted_index.patches | 5 |
| abstract_inverted_index.pixels. | 20 |
| abstract_inverted_index.propose | 114 |
| abstract_inverted_index.schemes | 61 |
| abstract_inverted_index.search, | 98 |
| abstract_inverted_index.success | 36 |
| abstract_inverted_index.trained | 138 |
| abstract_inverted_index.However, | 91 |
| abstract_inverted_index.ImageNet | 163 |
| abstract_inverted_index.[cs.CV], | 23 |
| abstract_inverted_index.accuracy | 146, 161 |
| abstract_inverted_index.anywhere | 179 |
| abstract_inverted_index.compute. | 132 |
| abstract_inverted_index.datasets | 156 |
| abstract_inverted_index.defense, | 27 |
| abstract_inverted_index.defenses | 2 |
| abstract_inverted_index.improves | 143 |
| abstract_inverted_index.location | 128 |
| abstract_inverted_index.masking, | 82 |
| abstract_inverted_index.masking. | 49 |
| abstract_inverted_index.maximize | 88 |
| abstract_inverted_index.problem, | 112 |
| abstract_inverted_index.requires | 95 |
| abstract_inverted_index.strategy | 31, 39, 119 |
| abstract_inverted_index.training | 60 |
| abstract_inverted_index.Certified | 159 |
| abstract_inverted_index.certified | 26, 144 |
| abstract_inverted_index.expensive | 103 |
| abstract_inverted_index.increases | 168 |
| abstract_inverted_index.introduce | 77 |
| abstract_inverted_index.selecting | 84 |
| abstract_inverted_index.training. | 108 |
| abstract_inverted_index.two-round | 116 |
| abstract_inverted_index.exhaustive | 97 |
| abstract_inverted_index.invariance | 45 |
| abstract_inverted_index.on-the-fly | 106 |
| abstract_inverted_index.prediction | 11 |
| abstract_inverted_index.worst-case | 81, 93, 126 |
| abstract_inverted_index.Certifiably | 0 |
| abstract_inverted_index.ViT-B16-224 | 166 |
| abstract_inverted_index.adversarial | 4 |
| abstract_inverted_index.approximate | 125 |
| abstract_inverted_index.classifiers | 8 |
| abstract_inverted_index.constrained | 17 |
| abstract_inverted_index.invariance. | 65 |
| abstract_inverted_index.neighborhood | 18 |
| abstract_inverted_index.PatchCleanser | 21, 151 |
| abstract_inverted_index.augmentations | 73 |
| abstract_inverted_index.prohibitively | 102 |
| abstract_inverted_index.PatchCleanser, | 75 |
| abstract_inverted_index.architectures. | 158 |
| abstract_inverted_index.classification | 89 |
| abstract_inverted_index.double-masking | 30 |
| abstract_inverted_index.classification. | 34 |
| abstract_inverted_index.arXiv:2108.09135 | 22 |
| abstract_inverted_index.state-of-the-art | 25 |
| abstract_inverted_index.arXiv:1708.04552v2 | 71 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.5799999833106995 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile |