Boosting Adversarial Transferability of MLP-Mixer Article Swipe
Haoran Lyu
,
Yajie Wang
,
Yu‐an Tan
,
Huipeng Zhou
,
Yuhang Zhao
,
Quanxin Zhang
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2204.12204
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2204.12204
The security of models based on new architectures such as MLP-Mixer and ViTs needs to be studied urgently. However, most of the current researches are mainly aimed at the adversarial attack against ViTs, and there is still relatively little adversarial work on MLP-mixer. We propose an adversarial attack method against MLP-Mixer called Maxwell's demon Attack (MA). MA breaks the channel-mixing and token-mixing mechanism of MLP-Mixer by controlling the part input of MLP-Mixer's each Mixer layer, and disturbs MLP-Mixer to obtain the main information of images. Our method can mask the part input of the Mixer layer, avoid overfitting of the adversarial examples to the source model, and improve the transferability of cross-architecture. Extensive experimental evaluation demonstrates the effectiveness and superior performance of the proposed MA. Our method can be easily combined with existing methods and can improve the transferability by up to 38.0% on MLP-based ResMLP. Adversarial examples produced by our method on MLP-Mixer are able to exceed the transferability of adversarial examples produced using DenseNet against CNNs. To the best of our knowledge, we are the first work to study adversarial transferability of MLP-Mixer.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2204.12204
- https://arxiv.org/pdf/2204.12204
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4224994149
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4224994149Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2204.12204Digital Object Identifier
- Title
-
Boosting Adversarial Transferability of MLP-MixerWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-04-26Full publication date if available
- Authors
-
Haoran Lyu, Yajie Wang, Yu‐an Tan, Huipeng Zhou, Yuhang Zhao, Quanxin ZhangList of authors in order
- Landing page
-
https://arxiv.org/abs/2204.12204Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2204.12204Direct 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/2204.12204Direct OA link when available
- Concepts
-
Transferability, Adversarial system, Computer science, Overfitting, Artificial intelligence, Security token, Pattern recognition (psychology), Machine learning, Artificial neural network, Computer security, LogitTop 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/W4224994149 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2204.12204 |
| ids.doi | https://doi.org/10.48550/arxiv.2204.12204 |
| ids.openalex | https://openalex.org/W4224994149 |
| fwci | |
| type | preprint |
| title | Boosting Adversarial Transferability of MLP-Mixer |
| 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 | 0.9995999932289124 |
| 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 | 0.9850999712944031 |
| 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/T12357 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9811999797821045 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Digital Media Forensic Detection |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C61272859 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8881521224975586 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7834031 |
| concepts[0].display_name | Transferability |
| concepts[1].id | https://openalex.org/C37736160 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7743970155715942 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[1].display_name | Adversarial system |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6998845934867859 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C22019652 |
| concepts[3].level | 3 |
| concepts[3].score | 0.6749005913734436 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q331309 |
| concepts[3].display_name | Overfitting |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.49457141757011414 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C48145219 |
| concepts[5].level | 2 |
| concepts[5].score | 0.43955400586128235 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1335365 |
| concepts[5].display_name | Security token |
| concepts[6].id | https://openalex.org/C153180895 |
| concepts[6].level | 2 |
| concepts[6].score | 0.3785649836063385 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[6].display_name | Pattern recognition (psychology) |
| concepts[7].id | https://openalex.org/C119857082 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3171490430831909 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[7].display_name | Machine learning |
| concepts[8].id | https://openalex.org/C50644808 |
| concepts[8].level | 2 |
| concepts[8].score | 0.2166615128517151 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[8].display_name | Artificial neural network |
| concepts[9].id | https://openalex.org/C38652104 |
| concepts[9].level | 1 |
| concepts[9].score | 0.1498464047908783 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[9].display_name | Computer security |
| concepts[10].id | https://openalex.org/C140331021 |
| concepts[10].level | 2 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q1868104 |
| concepts[10].display_name | Logit |
| keywords[0].id | https://openalex.org/keywords/transferability |
| keywords[0].score | 0.8881521224975586 |
| keywords[0].display_name | Transferability |
| keywords[1].id | https://openalex.org/keywords/adversarial-system |
| keywords[1].score | 0.7743970155715942 |
| keywords[1].display_name | Adversarial system |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6998845934867859 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/overfitting |
| keywords[3].score | 0.6749005913734436 |
| keywords[3].display_name | Overfitting |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.49457141757011414 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/security-token |
| keywords[5].score | 0.43955400586128235 |
| keywords[5].display_name | Security token |
| keywords[6].id | https://openalex.org/keywords/pattern-recognition |
| keywords[6].score | 0.3785649836063385 |
| keywords[6].display_name | Pattern recognition (psychology) |
| keywords[7].id | https://openalex.org/keywords/machine-learning |
| keywords[7].score | 0.3171490430831909 |
| keywords[7].display_name | Machine learning |
| keywords[8].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[8].score | 0.2166615128517151 |
| keywords[8].display_name | Artificial neural network |
| keywords[9].id | https://openalex.org/keywords/computer-security |
| keywords[9].score | 0.1498464047908783 |
| keywords[9].display_name | Computer security |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2204.12204 |
| 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/2204.12204 |
| 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/2204.12204 |
| locations[1].id | doi:10.48550/arxiv.2204.12204 |
| 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.2204.12204 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5077368865 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Haoran Lyu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Lyu, Haoran |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100455413 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-0962-4464 |
| authorships[1].author.display_name | Yajie Wang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wang, Yajie |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5003198271 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-6404-8853 |
| authorships[2].author.display_name | Yu‐an Tan |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Tan, Yu-an |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5029867593 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-4840-6558 |
| authorships[3].author.display_name | Huipeng Zhou |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhou, Huipeng |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5101756800 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-9598-5687 |
| authorships[4].author.display_name | Yuhang Zhao |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zhao, Yuhang |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5017675981 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-5094-7388 |
| authorships[5].author.display_name | Quanxin Zhang |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Zhang, Quanxin |
| authorships[5].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/2204.12204 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Boosting Adversarial Transferability of MLP-Mixer |
| 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 | 0.9995999932289124 |
| 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/W4288055406, https://openalex.org/W4200630034, https://openalex.org/W3137894200, https://openalex.org/W3092178728, https://openalex.org/W4226402597, https://openalex.org/W3132910851, https://openalex.org/W4377864639, https://openalex.org/W4392340763, https://openalex.org/W4283325551, https://openalex.org/W2997056298 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2204.12204 |
| 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/2204.12204 |
| 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/2204.12204 |
| primary_location.id | pmh:oai:arXiv.org:2204.12204 |
| 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/2204.12204 |
| 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/2204.12204 |
| publication_date | 2022-04-26 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.MA | 56 |
| abstract_inverted_index.To | 168 |
| abstract_inverted_index.We | 43 |
| abstract_inverted_index.an | 45 |
| abstract_inverted_index.as | 9 |
| abstract_inverted_index.at | 27 |
| abstract_inverted_index.be | 15, 128 |
| abstract_inverted_index.by | 65, 139, 149 |
| abstract_inverted_index.is | 35 |
| abstract_inverted_index.of | 2, 20, 63, 70, 83, 92, 98, 110, 121, 160, 171, 183 |
| abstract_inverted_index.on | 5, 41, 143, 152 |
| abstract_inverted_index.to | 14, 78, 102, 141, 156, 179 |
| abstract_inverted_index.up | 140 |
| abstract_inverted_index.we | 174 |
| abstract_inverted_index.MA. | 124 |
| abstract_inverted_index.Our | 85, 125 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 11, 33, 60, 75, 106, 118, 134 |
| abstract_inverted_index.are | 24, 154, 175 |
| abstract_inverted_index.can | 87, 127, 135 |
| abstract_inverted_index.new | 6 |
| abstract_inverted_index.our | 150, 172 |
| abstract_inverted_index.the | 21, 28, 58, 67, 80, 89, 93, 99, 103, 108, 116, 122, 137, 158, 169, 176 |
| abstract_inverted_index.ViTs | 12 |
| abstract_inverted_index.able | 155 |
| abstract_inverted_index.best | 170 |
| abstract_inverted_index.each | 72 |
| abstract_inverted_index.main | 81 |
| abstract_inverted_index.mask | 88 |
| abstract_inverted_index.most | 19 |
| abstract_inverted_index.part | 68, 90 |
| abstract_inverted_index.such | 8 |
| abstract_inverted_index.with | 131 |
| abstract_inverted_index.work | 40, 178 |
| abstract_inverted_index.(MA). | 55 |
| abstract_inverted_index.38.0% | 142 |
| abstract_inverted_index.CNNs. | 167 |
| abstract_inverted_index.Mixer | 73, 94 |
| abstract_inverted_index.ViTs, | 32 |
| abstract_inverted_index.aimed | 26 |
| abstract_inverted_index.avoid | 96 |
| abstract_inverted_index.based | 4 |
| abstract_inverted_index.demon | 53 |
| abstract_inverted_index.first | 177 |
| abstract_inverted_index.input | 69, 91 |
| abstract_inverted_index.needs | 13 |
| abstract_inverted_index.still | 36 |
| abstract_inverted_index.study | 180 |
| abstract_inverted_index.there | 34 |
| abstract_inverted_index.using | 164 |
| abstract_inverted_index.Attack | 54 |
| abstract_inverted_index.attack | 30, 47 |
| abstract_inverted_index.breaks | 57 |
| abstract_inverted_index.called | 51 |
| abstract_inverted_index.easily | 129 |
| abstract_inverted_index.exceed | 157 |
| abstract_inverted_index.layer, | 74, 95 |
| abstract_inverted_index.little | 38 |
| abstract_inverted_index.mainly | 25 |
| abstract_inverted_index.method | 48, 86, 126, 151 |
| abstract_inverted_index.model, | 105 |
| abstract_inverted_index.models | 3 |
| abstract_inverted_index.obtain | 79 |
| abstract_inverted_index.source | 104 |
| abstract_inverted_index.ResMLP. | 145 |
| abstract_inverted_index.against | 31, 49, 166 |
| abstract_inverted_index.current | 22 |
| abstract_inverted_index.images. | 84 |
| abstract_inverted_index.improve | 107, 136 |
| abstract_inverted_index.methods | 133 |
| abstract_inverted_index.propose | 44 |
| abstract_inverted_index.studied | 16 |
| abstract_inverted_index.DenseNet | 165 |
| abstract_inverted_index.However, | 18 |
| abstract_inverted_index.combined | 130 |
| abstract_inverted_index.disturbs | 76 |
| abstract_inverted_index.examples | 101, 147, 162 |
| abstract_inverted_index.existing | 132 |
| abstract_inverted_index.produced | 148, 163 |
| abstract_inverted_index.proposed | 123 |
| abstract_inverted_index.security | 1 |
| abstract_inverted_index.superior | 119 |
| abstract_inverted_index.Extensive | 112 |
| abstract_inverted_index.MLP-Mixer | 10, 50, 64, 77, 153 |
| abstract_inverted_index.MLP-based | 144 |
| abstract_inverted_index.Maxwell's | 52 |
| abstract_inverted_index.mechanism | 62 |
| abstract_inverted_index.urgently. | 17 |
| abstract_inverted_index.MLP-Mixer. | 184 |
| abstract_inverted_index.MLP-mixer. | 42 |
| abstract_inverted_index.evaluation | 114 |
| abstract_inverted_index.knowledge, | 173 |
| abstract_inverted_index.relatively | 37 |
| abstract_inverted_index.researches | 23 |
| abstract_inverted_index.Adversarial | 146 |
| abstract_inverted_index.MLP-Mixer's | 71 |
| abstract_inverted_index.adversarial | 29, 39, 46, 100, 161, 181 |
| abstract_inverted_index.controlling | 66 |
| abstract_inverted_index.information | 82 |
| abstract_inverted_index.overfitting | 97 |
| abstract_inverted_index.performance | 120 |
| abstract_inverted_index.demonstrates | 115 |
| abstract_inverted_index.experimental | 113 |
| abstract_inverted_index.token-mixing | 61 |
| abstract_inverted_index.architectures | 7 |
| abstract_inverted_index.effectiveness | 117 |
| abstract_inverted_index.channel-mixing | 59 |
| abstract_inverted_index.transferability | 109, 138, 159, 182 |
| abstract_inverted_index.cross-architecture. | 111 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/11 |
| sustainable_development_goals[0].score | 0.4099999964237213 |
| sustainable_development_goals[0].display_name | Sustainable cities and communities |
| citation_normalized_percentile |