Stop Diverse OOD Attacks: Knowledge Ensemble for Reliable Defense Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i19.34251
Enhancing defense through model ensemble is an emerging trend, where the challenge lies in how to use ensemble knowledge to counter Out-of-Distribution (OOD) attacks. In this paper, we propose the Reliable Defense Ensemble (REE) to address this issue. REE optimizes the ensemble knowledge of models through aggregation and enhances multidimensional robust performance through collaboration. It employs the Dynamic Synergy Amplification for weight allocation and strategy adjustment. Furthermore, we design a new Kernel Anomaly Smoothing Detection Module, which detects anomalous attacks using a smoothing feature function based on Gaussian kernel mean embedding and a multi-layer feedback structure. Particularly, we build a framework that uses reinforcement learning to iteratively fine-tune the parameters of inter-model communication and consensus. Extensive experimental results show that REE outperforms current state-of-the-art methods by a large margin in defending against OOD attacks.
Related Topics
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1609/aaai.v39i19.34251
- https://ojs.aaai.org/index.php/AAAI/article/download/34251/36406
- OA Status
- diamond
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4409363487
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4409363487Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1609/aaai.v39i19.34251Digital Object Identifier
- Title
-
Stop Diverse OOD Attacks: Knowledge Ensemble for Reliable DefenseWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-04-11Full publication date if available
- Authors
-
Zhenbo Shi, Xiaoman Liu, Yuxuan Zhang, Shuchang Wang, Rui Shu, Zhidong Yu, Wei Yang, Liusheng HuangList of authors in order
- Landing page
-
https://doi.org/10.1609/aaai.v39i19.34251Publisher landing page
- PDF URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/34251/36406Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/34251/36406Direct OA link when available
- Concepts
-
Computer science, Computer securityTop 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/W4409363487 |
|---|---|
| doi | https://doi.org/10.1609/aaai.v39i19.34251 |
| ids.doi | https://doi.org/10.1609/aaai.v39i19.34251 |
| ids.openalex | https://openalex.org/W4409363487 |
| fwci | 0.0 |
| type | article |
| title | Stop Diverse OOD Attacks: Knowledge Ensemble for Reliable Defense |
| biblio.issue | 19 |
| biblio.volume | 39 |
| biblio.last_page | 20444 |
| biblio.first_page | 20436 |
| topics[0].id | https://openalex.org/T10400 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9926000237464905 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1705 |
| topics[0].subfield.display_name | Computer Networks and Communications |
| topics[0].display_name | Network Security and Intrusion Detection |
| topics[1].id | https://openalex.org/T11241 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9764999747276306 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1711 |
| topics[1].subfield.display_name | Signal Processing |
| topics[1].display_name | Advanced Malware Detection Techniques |
| topics[2].id | https://openalex.org/T10734 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9646000266075134 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1710 |
| topics[2].subfield.display_name | Information Systems |
| topics[2].display_name | Information and Cyber Security |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.4547015130519867 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C38652104 |
| concepts[1].level | 1 |
| concepts[1].score | 0.3382062613964081 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[1].display_name | Computer security |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.4547015130519867 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/computer-security |
| keywords[1].score | 0.3382062613964081 |
| keywords[1].display_name | Computer security |
| language | en |
| locations[0].id | doi:10.1609/aaai.v39i19.34251 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210191458 |
| locations[0].source.issn | 2159-5399, 2374-3468 |
| locations[0].source.type | conference |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2159-5399 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].source.host_organization | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320058 |
| locations[0].license | |
| locations[0].pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/34251/36406 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].landing_page_url | https://doi.org/10.1609/aaai.v39i19.34251 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5078030239 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Zhenbo Shi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhenbo Shi |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5077840287 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Xiaoman Liu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xiaoman Liu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100319905 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-3760-1083 |
| authorships[2].author.display_name | Yuxuan Zhang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Yuxuan Zhang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5087258671 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-8191-1188 |
| authorships[3].author.display_name | Shuchang Wang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Shuchang Wang |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100746782 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-8937-7274 |
| authorships[4].author.display_name | Rui Shu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Rui Shu |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5113536741 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-7168-6423 |
| authorships[5].author.display_name | Zhidong Yu |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Zhidong Yu |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5100613524 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-5338-7347 |
| authorships[6].author.display_name | Wei Yang |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Wei Yang |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5019604942 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-8417-3256 |
| authorships[7].author.display_name | Liusheng Huang |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Liusheng Huang |
| authorships[7].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ojs.aaai.org/index.php/AAAI/article/download/34251/36406 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Stop Diverse OOD Attacks: Knowledge Ensemble for Reliable Defense |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10400 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9926000237464905 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1705 |
| primary_topic.subfield.display_name | Computer Networks and Communications |
| primary_topic.display_name | Network Security and Intrusion Detection |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1609/aaai.v39i19.34251 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210191458 |
| best_oa_location.source.issn | 2159-5399, 2374-3468 |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2159-5399 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.source.host_organization | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/34251/36406 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.landing_page_url | https://doi.org/10.1609/aaai.v39i19.34251 |
| primary_location.id | doi:10.1609/aaai.v39i19.34251 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210191458 |
| primary_location.source.issn | 2159-5399, 2374-3468 |
| primary_location.source.type | conference |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2159-5399 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.source.host_organization | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| primary_location.license | |
| primary_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/34251/36406 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.landing_page_url | https://doi.org/10.1609/aaai.v39i19.34251 |
| publication_date | 2025-04-11 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 69, 81, 92, 99, 126 |
| abstract_inverted_index.In | 24 |
| abstract_inverted_index.It | 54 |
| abstract_inverted_index.an | 6 |
| abstract_inverted_index.by | 125 |
| abstract_inverted_index.in | 13, 129 |
| abstract_inverted_index.is | 5 |
| abstract_inverted_index.of | 43, 110 |
| abstract_inverted_index.on | 86 |
| abstract_inverted_index.to | 15, 19, 34, 105 |
| abstract_inverted_index.we | 27, 67, 97 |
| abstract_inverted_index.OOD | 132 |
| abstract_inverted_index.REE | 38, 120 |
| abstract_inverted_index.and | 47, 63, 91, 113 |
| abstract_inverted_index.for | 60 |
| abstract_inverted_index.how | 14 |
| abstract_inverted_index.new | 70 |
| abstract_inverted_index.the | 10, 29, 40, 56, 108 |
| abstract_inverted_index.use | 16 |
| abstract_inverted_index.lies | 12 |
| abstract_inverted_index.mean | 89 |
| abstract_inverted_index.show | 118 |
| abstract_inverted_index.that | 101, 119 |
| abstract_inverted_index.this | 25, 36 |
| abstract_inverted_index.uses | 102 |
| abstract_inverted_index.(OOD) | 22 |
| abstract_inverted_index.(REE) | 33 |
| abstract_inverted_index.based | 85 |
| abstract_inverted_index.build | 98 |
| abstract_inverted_index.large | 127 |
| abstract_inverted_index.model | 3 |
| abstract_inverted_index.using | 80 |
| abstract_inverted_index.where | 9 |
| abstract_inverted_index.which | 76 |
| abstract_inverted_index.Kernel | 71 |
| abstract_inverted_index.design | 68 |
| abstract_inverted_index.issue. | 37 |
| abstract_inverted_index.kernel | 88 |
| abstract_inverted_index.margin | 128 |
| abstract_inverted_index.models | 44 |
| abstract_inverted_index.paper, | 26 |
| abstract_inverted_index.robust | 50 |
| abstract_inverted_index.trend, | 8 |
| abstract_inverted_index.weight | 61 |
| abstract_inverted_index.Anomaly | 72 |
| abstract_inverted_index.Defense | 31 |
| abstract_inverted_index.Dynamic | 57 |
| abstract_inverted_index.Module, | 75 |
| abstract_inverted_index.Synergy | 58 |
| abstract_inverted_index.address | 35 |
| abstract_inverted_index.against | 131 |
| abstract_inverted_index.attacks | 79 |
| abstract_inverted_index.counter | 20 |
| abstract_inverted_index.current | 122 |
| abstract_inverted_index.defense | 1 |
| abstract_inverted_index.detects | 77 |
| abstract_inverted_index.employs | 55 |
| abstract_inverted_index.feature | 83 |
| abstract_inverted_index.methods | 124 |
| abstract_inverted_index.propose | 28 |
| abstract_inverted_index.results | 117 |
| abstract_inverted_index.through | 2, 45, 52 |
| abstract_inverted_index.Ensemble | 32 |
| abstract_inverted_index.Gaussian | 87 |
| abstract_inverted_index.Reliable | 30 |
| abstract_inverted_index.attacks. | 23, 133 |
| abstract_inverted_index.emerging | 7 |
| abstract_inverted_index.enhances | 48 |
| abstract_inverted_index.ensemble | 4, 17, 41 |
| abstract_inverted_index.feedback | 94 |
| abstract_inverted_index.function | 84 |
| abstract_inverted_index.learning | 104 |
| abstract_inverted_index.strategy | 64 |
| abstract_inverted_index.Detection | 74 |
| abstract_inverted_index.Enhancing | 0 |
| abstract_inverted_index.Extensive | 115 |
| abstract_inverted_index.Smoothing | 73 |
| abstract_inverted_index.anomalous | 78 |
| abstract_inverted_index.challenge | 11 |
| abstract_inverted_index.defending | 130 |
| abstract_inverted_index.embedding | 90 |
| abstract_inverted_index.fine-tune | 107 |
| abstract_inverted_index.framework | 100 |
| abstract_inverted_index.knowledge | 18, 42 |
| abstract_inverted_index.optimizes | 39 |
| abstract_inverted_index.smoothing | 82 |
| abstract_inverted_index.allocation | 62 |
| abstract_inverted_index.consensus. | 114 |
| abstract_inverted_index.parameters | 109 |
| abstract_inverted_index.structure. | 95 |
| abstract_inverted_index.adjustment. | 65 |
| abstract_inverted_index.aggregation | 46 |
| abstract_inverted_index.inter-model | 111 |
| abstract_inverted_index.iteratively | 106 |
| abstract_inverted_index.multi-layer | 93 |
| abstract_inverted_index.outperforms | 121 |
| abstract_inverted_index.performance | 51 |
| abstract_inverted_index.Furthermore, | 66 |
| abstract_inverted_index.experimental | 116 |
| abstract_inverted_index.Amplification | 59 |
| abstract_inverted_index.Particularly, | 96 |
| abstract_inverted_index.communication | 112 |
| abstract_inverted_index.reinforcement | 103 |
| abstract_inverted_index.collaboration. | 53 |
| abstract_inverted_index.multidimensional | 49 |
| abstract_inverted_index.state-of-the-art | 123 |
| abstract_inverted_index.Out-of-Distribution | 21 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile.value | 0.25641026 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |