AEAED: Attention-Enhanced Autoencoder for Adversarial Example Detection with Multi-Scale Feature Learning Article Swipe
Ming He
,
Mengyao Cui
,
Yanchun Liang
,
Hanqi Liu
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.62517/jike.202404313
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.62517/jike.202404313
Deep learning models face significant security threats from adversarial attacks, which can mislead model predictions by introducing subtle perturbations to input images. Existing adversarial example detection methods often suffer from limited detection accuracy and poor generalization capabilities. To address these challenges, we propose AEAED (Attention-Enhanced Autoencoder for Adversarial Example Detection with Multi-Scale Feature Learning), a novel detection model that integrates Transformer's multi-head self-attention mechanism into an autoencoder framework, significantly enhancing the model's ability to capture both global and local image features. AEAED comprises three key components: (1) a multi-scale attention encoder that combines convolutional layers' local feature extraction capabilities with self-attention mechanisms for global dependency modeling, improving sensitivity to adversarial perturbations; (2) an adaptive reconstruction decoder that leverages multi-head self-attention mechanisms to achieve high-quality image reconstruction; and (3) a comprehensive reconstruction error calculation method that integrates pixel-level errors and feature layer discrepancies, coupled with an adaptive threshold strategy for adversarial example detection. Experimental results on the CIFAR-10 dataset demonstrate that AEAED significantly outperforms existing baseline models, including MagNet, DAGMM, and SafetyNet, across multiple evaluation metrics. Notably, when detecting FGSM adversarial examples generated using the Swin Transformer, the model achieves an accuracy of 87.10%, a recall of 85.40%, and an AUC-ROC value of 0.89, while reducing the false positive rate to 0.08. These results conclusively validate the effectiveness and superiority of the proposed method in adversarial example detection tasks.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.62517/jike.202404313
- http://www.stemmpress.com/uploadfile/202411/b8f4da634cb8eea.pdf
- OA Status
- hybrid
- References
- 21
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4409891633
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4409891633Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.62517/jike.202404313Digital Object Identifier
- Title
-
AEAED: Attention-Enhanced Autoencoder for Adversarial Example Detection with Multi-Scale Feature LearningWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-09-01Full publication date if available
- Authors
-
Ming He, Mengyao Cui, Yanchun Liang, Hanqi LiuList of authors in order
- Landing page
-
https://doi.org/10.62517/jike.202404313Publisher landing page
- PDF URL
-
https://www.stemmpress.com/uploadfile/202411/b8f4da634cb8eea.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://www.stemmpress.com/uploadfile/202411/b8f4da634cb8eea.pdfDirect OA link when available
- Concepts
-
Autoencoder, Adversarial system, Artificial intelligence, Feature (linguistics), Scale (ratio), Computer science, Feature learning, Machine learning, Pattern recognition (psychology), Deep learning, Geography, Philosophy, Linguistics, CartographyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
21Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4409891633 |
|---|---|
| doi | https://doi.org/10.62517/jike.202404313 |
| ids.doi | https://doi.org/10.62517/jike.202404313 |
| ids.openalex | https://openalex.org/W4409891633 |
| fwci | 0.0 |
| type | article |
| title | AEAED: Attention-Enhanced Autoencoder for Adversarial Example Detection with Multi-Scale Feature Learning |
| biblio.issue | 3 |
| biblio.volume | 2 |
| biblio.last_page | 106 |
| biblio.first_page | 99 |
| 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/T11512 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9883000254631042 |
| 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/T14117 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9868999719619751 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2208 |
| topics[2].subfield.display_name | Electrical and Electronic Engineering |
| topics[2].display_name | Integrated Circuits and Semiconductor Failure Analysis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C101738243 |
| concepts[0].level | 3 |
| concepts[0].score | 0.9101617932319641 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q786435 |
| concepts[0].display_name | Autoencoder |
| concepts[1].id | https://openalex.org/C37736160 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7247300744056702 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[1].display_name | Adversarial system |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6587605476379395 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C2776401178 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6574869155883789 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[3].display_name | Feature (linguistics) |
| concepts[4].id | https://openalex.org/C2778755073 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5557180047035217 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q10858537 |
| concepts[4].display_name | Scale (ratio) |
| concepts[5].id | https://openalex.org/C41008148 |
| concepts[5].level | 0 |
| concepts[5].score | 0.5384580492973328 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[5].display_name | Computer science |
| concepts[6].id | https://openalex.org/C59404180 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4788227677345276 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q17013334 |
| concepts[6].display_name | Feature learning |
| concepts[7].id | https://openalex.org/C119857082 |
| concepts[7].level | 1 |
| concepts[7].score | 0.42919617891311646 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[7].display_name | Machine learning |
| concepts[8].id | https://openalex.org/C153180895 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4035439193248749 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[8].display_name | Pattern recognition (psychology) |
| concepts[9].id | https://openalex.org/C108583219 |
| concepts[9].level | 2 |
| concepts[9].score | 0.31660136580467224 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[9].display_name | Deep learning |
| concepts[10].id | https://openalex.org/C205649164 |
| concepts[10].level | 0 |
| concepts[10].score | 0.10091385245323181 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[10].display_name | Geography |
| concepts[11].id | https://openalex.org/C138885662 |
| concepts[11].level | 0 |
| concepts[11].score | 0.08250382542610168 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[11].display_name | Philosophy |
| concepts[12].id | https://openalex.org/C41895202 |
| concepts[12].level | 1 |
| concepts[12].score | 0.07085555791854858 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[12].display_name | Linguistics |
| concepts[13].id | https://openalex.org/C58640448 |
| concepts[13].level | 1 |
| concepts[13].score | 0.07042765617370605 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q42515 |
| concepts[13].display_name | Cartography |
| keywords[0].id | https://openalex.org/keywords/autoencoder |
| keywords[0].score | 0.9101617932319641 |
| keywords[0].display_name | Autoencoder |
| keywords[1].id | https://openalex.org/keywords/adversarial-system |
| keywords[1].score | 0.7247300744056702 |
| keywords[1].display_name | Adversarial system |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6587605476379395 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/feature |
| keywords[3].score | 0.6574869155883789 |
| keywords[3].display_name | Feature (linguistics) |
| keywords[4].id | https://openalex.org/keywords/scale |
| keywords[4].score | 0.5557180047035217 |
| keywords[4].display_name | Scale (ratio) |
| keywords[5].id | https://openalex.org/keywords/computer-science |
| keywords[5].score | 0.5384580492973328 |
| keywords[5].display_name | Computer science |
| keywords[6].id | https://openalex.org/keywords/feature-learning |
| keywords[6].score | 0.4788227677345276 |
| keywords[6].display_name | Feature learning |
| keywords[7].id | https://openalex.org/keywords/machine-learning |
| keywords[7].score | 0.42919617891311646 |
| keywords[7].display_name | Machine learning |
| keywords[8].id | https://openalex.org/keywords/pattern-recognition |
| keywords[8].score | 0.4035439193248749 |
| keywords[8].display_name | Pattern recognition (psychology) |
| keywords[9].id | https://openalex.org/keywords/deep-learning |
| keywords[9].score | 0.31660136580467224 |
| keywords[9].display_name | Deep learning |
| keywords[10].id | https://openalex.org/keywords/geography |
| keywords[10].score | 0.10091385245323181 |
| keywords[10].display_name | Geography |
| keywords[11].id | https://openalex.org/keywords/philosophy |
| keywords[11].score | 0.08250382542610168 |
| keywords[11].display_name | Philosophy |
| keywords[12].id | https://openalex.org/keywords/linguistics |
| keywords[12].score | 0.07085555791854858 |
| keywords[12].display_name | Linguistics |
| keywords[13].id | https://openalex.org/keywords/cartography |
| keywords[13].score | 0.07042765617370605 |
| keywords[13].display_name | Cartography |
| language | en |
| locations[0].id | doi:10.62517/jike.202404313 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4404669749 |
| locations[0].source.issn | 2959-0620 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 2959-0620 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Journal of intelligence and knowledge engineering. |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | cc-by |
| locations[0].pdf_url | http://www.stemmpress.com/uploadfile/202411/b8f4da634cb8eea.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Journal of Intelligence and Knowledge Engineering |
| locations[0].landing_page_url | https://doi.org/10.62517/jike.202404313 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5032567326 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1414-4027 |
| authorships[0].author.display_name | Ming He |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ming He |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5004339625 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Mengyao Cui |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Mengyao Cui |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5076665413 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-1147-3968 |
| authorships[2].author.display_name | Yanchun Liang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Yanbing Liang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5108988977 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Hanqi Liu |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Hanqi Liu |
| authorships[3].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | http://www.stemmpress.com/uploadfile/202411/b8f4da634cb8eea.pdf |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | AEAED: Attention-Enhanced Autoencoder for Adversarial Example Detection with Multi-Scale Feature Learning |
| 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/W2669956259, https://openalex.org/W4249005693, https://openalex.org/W4392946183, https://openalex.org/W4405887298, https://openalex.org/W2619203976, https://openalex.org/W2983142544, https://openalex.org/W2891059443, https://openalex.org/W4281663961, https://openalex.org/W3208888551, https://openalex.org/W4313561566 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.62517/jike.202404313 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4404669749 |
| best_oa_location.source.issn | 2959-0620 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 2959-0620 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Journal of intelligence and knowledge engineering. |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | http://www.stemmpress.com/uploadfile/202411/b8f4da634cb8eea.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Journal of Intelligence and Knowledge Engineering |
| best_oa_location.landing_page_url | https://doi.org/10.62517/jike.202404313 |
| primary_location.id | doi:10.62517/jike.202404313 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4404669749 |
| primary_location.source.issn | 2959-0620 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 2959-0620 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Journal of intelligence and knowledge engineering. |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | cc-by |
| primary_location.pdf_url | http://www.stemmpress.com/uploadfile/202411/b8f4da634cb8eea.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Journal of Intelligence and Knowledge Engineering |
| primary_location.landing_page_url | https://doi.org/10.62517/jike.202404313 |
| publication_date | 2024-09-01 |
| publication_year | 2024 |
| referenced_works | https://openalex.org/W6637162671, https://openalex.org/W1945616565, https://openalex.org/W2963542245, https://openalex.org/W2963857521, https://openalex.org/W4287020936, https://openalex.org/W4393178853, https://openalex.org/W4386565699, https://openalex.org/W3208354430, https://openalex.org/W4385521756, https://openalex.org/W4289821784, https://openalex.org/W3041355024, https://openalex.org/W4319073662, https://openalex.org/W4280628446, https://openalex.org/W2611576673, https://openalex.org/W4403024540, https://openalex.org/W2618043096, https://openalex.org/W6734787559, https://openalex.org/W3094502228, https://openalex.org/W3138516171, https://openalex.org/W4402726980, https://openalex.org/W4384648484 |
| referenced_works_count | 21 |
| abstract_inverted_index.a | 54, 87, 128, 193 |
| abstract_inverted_index.To | 37 |
| abstract_inverted_index.an | 65, 112, 144, 189, 198 |
| abstract_inverted_index.by | 15 |
| abstract_inverted_index.in | 223 |
| abstract_inverted_index.of | 191, 195, 201, 219 |
| abstract_inverted_index.on | 154 |
| abstract_inverted_index.to | 19, 73, 108, 121, 209 |
| abstract_inverted_index.we | 41 |
| abstract_inverted_index.(1) | 86 |
| abstract_inverted_index.(2) | 111 |
| abstract_inverted_index.(3) | 127 |
| abstract_inverted_index.and | 33, 77, 126, 138, 169, 197, 217 |
| abstract_inverted_index.can | 11 |
| abstract_inverted_index.for | 46, 102, 148 |
| abstract_inverted_index.key | 84 |
| abstract_inverted_index.the | 70, 155, 183, 186, 205, 215, 220 |
| abstract_inverted_index.Deep | 0 |
| abstract_inverted_index.FGSM | 178 |
| abstract_inverted_index.Swin | 184 |
| abstract_inverted_index.both | 75 |
| abstract_inverted_index.face | 3 |
| abstract_inverted_index.from | 7, 29 |
| abstract_inverted_index.into | 64 |
| abstract_inverted_index.poor | 34 |
| abstract_inverted_index.rate | 208 |
| abstract_inverted_index.that | 58, 91, 116, 134, 159 |
| abstract_inverted_index.when | 176 |
| abstract_inverted_index.with | 50, 99, 143 |
| abstract_inverted_index.0.08. | 210 |
| abstract_inverted_index.0.89, | 202 |
| abstract_inverted_index.AEAED | 43, 81, 160 |
| abstract_inverted_index.These | 211 |
| abstract_inverted_index.error | 131 |
| abstract_inverted_index.false | 206 |
| abstract_inverted_index.image | 79, 124 |
| abstract_inverted_index.input | 20 |
| abstract_inverted_index.layer | 140 |
| abstract_inverted_index.local | 78, 95 |
| abstract_inverted_index.model | 13, 57, 187 |
| abstract_inverted_index.novel | 55 |
| abstract_inverted_index.often | 27 |
| abstract_inverted_index.these | 39 |
| abstract_inverted_index.three | 83 |
| abstract_inverted_index.using | 182 |
| abstract_inverted_index.value | 200 |
| abstract_inverted_index.which | 10 |
| abstract_inverted_index.while | 203 |
| abstract_inverted_index.DAGMM, | 168 |
| abstract_inverted_index.across | 171 |
| abstract_inverted_index.errors | 137 |
| abstract_inverted_index.global | 76, 103 |
| abstract_inverted_index.method | 133, 222 |
| abstract_inverted_index.models | 2 |
| abstract_inverted_index.recall | 194 |
| abstract_inverted_index.subtle | 17 |
| abstract_inverted_index.suffer | 28 |
| abstract_inverted_index.tasks. | 227 |
| abstract_inverted_index.85.40%, | 196 |
| abstract_inverted_index.87.10%, | 192 |
| abstract_inverted_index.AUC-ROC | 199 |
| abstract_inverted_index.Example | 48 |
| abstract_inverted_index.Feature | 52 |
| abstract_inverted_index.MagNet, | 167 |
| abstract_inverted_index.ability | 72 |
| abstract_inverted_index.achieve | 122 |
| abstract_inverted_index.address | 38 |
| abstract_inverted_index.capture | 74 |
| abstract_inverted_index.coupled | 142 |
| abstract_inverted_index.dataset | 157 |
| abstract_inverted_index.decoder | 115 |
| abstract_inverted_index.encoder | 90 |
| abstract_inverted_index.example | 24, 150, 225 |
| abstract_inverted_index.feature | 96, 139 |
| abstract_inverted_index.images. | 21 |
| abstract_inverted_index.layers' | 94 |
| abstract_inverted_index.limited | 30 |
| abstract_inverted_index.methods | 26 |
| abstract_inverted_index.mislead | 12 |
| abstract_inverted_index.model's | 71 |
| abstract_inverted_index.models, | 165 |
| abstract_inverted_index.propose | 42 |
| abstract_inverted_index.results | 153, 212 |
| abstract_inverted_index.threats | 6 |
| abstract_inverted_index.CIFAR-10 | 156 |
| abstract_inverted_index.Existing | 22 |
| abstract_inverted_index.Notably, | 175 |
| abstract_inverted_index.accuracy | 32, 190 |
| abstract_inverted_index.achieves | 188 |
| abstract_inverted_index.adaptive | 113, 145 |
| abstract_inverted_index.attacks, | 9 |
| abstract_inverted_index.baseline | 164 |
| abstract_inverted_index.combines | 92 |
| abstract_inverted_index.examples | 180 |
| abstract_inverted_index.existing | 163 |
| abstract_inverted_index.learning | 1 |
| abstract_inverted_index.metrics. | 174 |
| abstract_inverted_index.multiple | 172 |
| abstract_inverted_index.positive | 207 |
| abstract_inverted_index.proposed | 221 |
| abstract_inverted_index.reducing | 204 |
| abstract_inverted_index.security | 5 |
| abstract_inverted_index.strategy | 147 |
| abstract_inverted_index.validate | 214 |
| abstract_inverted_index.Detection | 49 |
| abstract_inverted_index.attention | 89 |
| abstract_inverted_index.comprises | 82 |
| abstract_inverted_index.detecting | 177 |
| abstract_inverted_index.detection | 25, 31, 56, 226 |
| abstract_inverted_index.enhancing | 69 |
| abstract_inverted_index.features. | 80 |
| abstract_inverted_index.generated | 181 |
| abstract_inverted_index.improving | 106 |
| abstract_inverted_index.including | 166 |
| abstract_inverted_index.leverages | 117 |
| abstract_inverted_index.mechanism | 63 |
| abstract_inverted_index.modeling, | 105 |
| abstract_inverted_index.threshold | 146 |
| abstract_inverted_index.Learning), | 53 |
| abstract_inverted_index.SafetyNet, | 170 |
| abstract_inverted_index.dependency | 104 |
| abstract_inverted_index.detection. | 151 |
| abstract_inverted_index.evaluation | 173 |
| abstract_inverted_index.extraction | 97 |
| abstract_inverted_index.framework, | 67 |
| abstract_inverted_index.integrates | 59, 135 |
| abstract_inverted_index.mechanisms | 101, 120 |
| abstract_inverted_index.multi-head | 61, 118 |
| abstract_inverted_index.Adversarial | 47 |
| abstract_inverted_index.Autoencoder | 45 |
| abstract_inverted_index.Multi-Scale | 51 |
| abstract_inverted_index.adversarial | 8, 23, 109, 149, 179, 224 |
| abstract_inverted_index.autoencoder | 66 |
| abstract_inverted_index.calculation | 132 |
| abstract_inverted_index.challenges, | 40 |
| abstract_inverted_index.components: | 85 |
| abstract_inverted_index.demonstrate | 158 |
| abstract_inverted_index.introducing | 16 |
| abstract_inverted_index.multi-scale | 88 |
| abstract_inverted_index.outperforms | 162 |
| abstract_inverted_index.pixel-level | 136 |
| abstract_inverted_index.predictions | 14 |
| abstract_inverted_index.sensitivity | 107 |
| abstract_inverted_index.significant | 4 |
| abstract_inverted_index.superiority | 218 |
| abstract_inverted_index.Experimental | 152 |
| abstract_inverted_index.Transformer, | 185 |
| abstract_inverted_index.capabilities | 98 |
| abstract_inverted_index.conclusively | 213 |
| abstract_inverted_index.high-quality | 123 |
| abstract_inverted_index.Transformer's | 60 |
| abstract_inverted_index.capabilities. | 36 |
| abstract_inverted_index.comprehensive | 129 |
| abstract_inverted_index.convolutional | 93 |
| abstract_inverted_index.effectiveness | 216 |
| abstract_inverted_index.perturbations | 18 |
| abstract_inverted_index.significantly | 68, 161 |
| abstract_inverted_index.discrepancies, | 141 |
| abstract_inverted_index.generalization | 35 |
| abstract_inverted_index.perturbations; | 110 |
| abstract_inverted_index.reconstruction | 114, 130 |
| abstract_inverted_index.self-attention | 62, 100, 119 |
| abstract_inverted_index.reconstruction; | 125 |
| abstract_inverted_index.(Attention-Enhanced | 44 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile.value | 0.32712149 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |