Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors Article Swipe
Pooya Tavallali
,
Vahid Behzadan
,
Peyman Tavallali
,
Mukesh Singhal
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2102.05867
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2102.05867
State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques that are only applicable to specific machine learning models. Additionally, the existing data poisoning attacks in the literature are limited to either binary classifiers or to gradient-based algorithms. To address these limitations, this paper first proposes a novel model-free label-flipping attack based on the multi-modality of the data, in which the adversary targets the clusters of classes while constrained by a label-flipping budget. The complexity of our proposed attack algorithm is linear in time over the size of the dataset. Also, the proposed attack can increase the error up to two times for the same attack budget. Second, a novel defense technique based on the Synthetic Reduced Nearest Neighbor (SRNN) model is proposed. The defense technique can detect and exclude flipped samples on the fly during the training procedure. Through extensive experimental analysis, we demonstrate that (i) the proposed attack technique can deteriorate the accuracy of several models drastically, and (ii) under the proposed attack, the proposed defense technique significantly outperforms other conventional machine learning models in recovering the accuracy of the targeted model.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2102.05867
- https://arxiv.org/pdf/2102.05867
- OA Status
- green
- Cited By
- 1
- References
- 45
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3127195467
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3127195467Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2102.05867Digital Object Identifier
- Title
-
Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest NeighborsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-02-11Full publication date if available
- Authors
-
Pooya Tavallali, Vahid Behzadan, Peyman Tavallali, Mukesh SinghalList of authors in order
- Landing page
-
https://arxiv.org/abs/2102.05867Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2102.05867Direct 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/2102.05867Direct OA link when available
- Concepts
-
Computer science, Artificial intelligence, Attack model, Adversary, Machine learning, Class (philosophy), k-nearest neighbors algorithm, Adversarial system, Data mining, Computer securityTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2021: 1Per-year citation counts (last 5 years)
- References (count)
-
45Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3127195467 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2102.05867 |
| ids.doi | https://doi.org/10.48550/arxiv.2102.05867 |
| ids.mag | 3127195467 |
| ids.openalex | https://openalex.org/W3127195467 |
| fwci | |
| type | preprint |
| title | Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors |
| 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 | 0.9998999834060669 |
| 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 | 0.9993000030517578 |
| 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/T10400 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9858999848365784 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1705 |
| topics[2].subfield.display_name | Computer Networks and Communications |
| topics[2].display_name | Network Security and Intrusion Detection |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7824722528457642 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C154945302 |
| concepts[1].level | 1 |
| concepts[1].score | 0.579690158367157 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[1].display_name | Artificial intelligence |
| concepts[2].id | https://openalex.org/C65856478 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5640578866004944 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q3991682 |
| concepts[2].display_name | Attack model |
| concepts[3].id | https://openalex.org/C41065033 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5625067353248596 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2825412 |
| concepts[3].display_name | Adversary |
| concepts[4].id | https://openalex.org/C119857082 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5395563840866089 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[4].display_name | Machine learning |
| concepts[5].id | https://openalex.org/C2777212361 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5200875997543335 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[5].display_name | Class (philosophy) |
| concepts[6].id | https://openalex.org/C113238511 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5106273293495178 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1071612 |
| concepts[6].display_name | k-nearest neighbors algorithm |
| concepts[7].id | https://openalex.org/C37736160 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4481392204761505 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[7].display_name | Adversarial system |
| concepts[8].id | https://openalex.org/C124101348 |
| concepts[8].level | 1 |
| concepts[8].score | 0.33281588554382324 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q172491 |
| concepts[8].display_name | Data mining |
| concepts[9].id | https://openalex.org/C38652104 |
| concepts[9].level | 1 |
| concepts[9].score | 0.24795293807983398 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[9].display_name | Computer security |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7824722528457642 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[1].score | 0.579690158367157 |
| keywords[1].display_name | Artificial intelligence |
| keywords[2].id | https://openalex.org/keywords/attack-model |
| keywords[2].score | 0.5640578866004944 |
| keywords[2].display_name | Attack model |
| keywords[3].id | https://openalex.org/keywords/adversary |
| keywords[3].score | 0.5625067353248596 |
| keywords[3].display_name | Adversary |
| keywords[4].id | https://openalex.org/keywords/machine-learning |
| keywords[4].score | 0.5395563840866089 |
| keywords[4].display_name | Machine learning |
| keywords[5].id | https://openalex.org/keywords/class |
| keywords[5].score | 0.5200875997543335 |
| keywords[5].display_name | Class (philosophy) |
| keywords[6].id | https://openalex.org/keywords/k-nearest-neighbors-algorithm |
| keywords[6].score | 0.5106273293495178 |
| keywords[6].display_name | k-nearest neighbors algorithm |
| keywords[7].id | https://openalex.org/keywords/adversarial-system |
| keywords[7].score | 0.4481392204761505 |
| keywords[7].display_name | Adversarial system |
| keywords[8].id | https://openalex.org/keywords/data-mining |
| keywords[8].score | 0.33281588554382324 |
| keywords[8].display_name | Data mining |
| keywords[9].id | https://openalex.org/keywords/computer-security |
| keywords[9].score | 0.24795293807983398 |
| keywords[9].display_name | Computer security |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2102.05867 |
| 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/2102.05867 |
| 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/2102.05867 |
| locations[1].id | mag:3127195467 |
| 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 | submittedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | arXiv (Cornell University) |
| locations[1].landing_page_url | https://arxiv.org/pdf/2102.05867.pdf |
| locations[2].id | doi:10.48550/arxiv.2102.05867 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | public-domain |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | article |
| locations[2].license_id | https://openalex.org/licenses/public-domain |
| locations[2].is_accepted | False |
| locations[2].is_published | |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | https://doi.org/10.48550/arxiv.2102.05867 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5043065282 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-6847-2387 |
| authorships[0].author.display_name | Pooya Tavallali |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I156087764 |
| authorships[0].affiliations[0].raw_affiliation_string | University of California Merced |
| authorships[0].institutions[0].id | https://openalex.org/I156087764 |
| authorships[0].institutions[0].ror | https://ror.org/00d9ah105 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I156087764 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | University of California, Merced |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Pooya Tavallali |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | University of California Merced |
| authorships[1].author.id | https://openalex.org/A5062734917 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Vahid Behzadan |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I40253897 |
| authorships[1].affiliations[0].raw_affiliation_string | University of New Haven#TAB# |
| authorships[1].institutions[0].id | https://openalex.org/I40253897 |
| authorships[1].institutions[0].ror | https://ror.org/00zm4rq24 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I40253897 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | University of New Haven |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Vahid Behzadan |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | University of New Haven#TAB# |
| authorships[2].author.id | https://openalex.org/A5049660620 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7166-5489 |
| authorships[2].author.display_name | Peyman Tavallali |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Peyman Tavallali |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5058282709 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0497-1942 |
| authorships[3].author.display_name | Mukesh Singhal |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I156087764 |
| authorships[3].affiliations[0].raw_affiliation_string | University of California Merced |
| authorships[3].institutions[0].id | https://openalex.org/I156087764 |
| authorships[3].institutions[0].ror | https://ror.org/00d9ah105 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I156087764 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | University of California, Merced |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Mukesh Singhal |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | University of California Merced |
| 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/2102.05867 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors |
| 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 | 0.9998999834060669 |
| 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/W2914433962, https://openalex.org/W2998625988, https://openalex.org/W3007692662, https://openalex.org/W2146211964, https://openalex.org/W2987019399, https://openalex.org/W3127927415, https://openalex.org/W3001846878, https://openalex.org/W3208322257, https://openalex.org/W2932048622, https://openalex.org/W3214326666, https://openalex.org/W3105976275, https://openalex.org/W2895097814, https://openalex.org/W2913505432, https://openalex.org/W3198892687, https://openalex.org/W2773246606, https://openalex.org/W3165917199, https://openalex.org/W3048133945, https://openalex.org/W3046449280, https://openalex.org/W3168142805, https://openalex.org/W2913144408 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2021 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 3 |
| best_oa_location.id | pmh:oai:arXiv.org:2102.05867 |
| 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/2102.05867 |
| 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/2102.05867 |
| primary_location.id | pmh:oai:arXiv.org:2102.05867 |
| 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/2102.05867 |
| 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/2102.05867 |
| publication_date | 2021-02-11 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W1670346950, https://openalex.org/W2172059508, https://openalex.org/W2122111042, https://openalex.org/W2143074819, https://openalex.org/W2138457014, https://openalex.org/W1515620500, https://openalex.org/W2168873314, https://openalex.org/W2079899298, https://openalex.org/W2137130182, https://openalex.org/W1968411139, https://openalex.org/W2732039841, https://openalex.org/W2142279020, https://openalex.org/W2949506549, https://openalex.org/W2964074004, https://openalex.org/W1973598714, https://openalex.org/W1605688901, https://openalex.org/W2151298633, https://openalex.org/W2156267802, https://openalex.org/W1554944419, https://openalex.org/W2150593711, https://openalex.org/W2105037940, https://openalex.org/W2122646361, https://openalex.org/W2293844262, https://openalex.org/W1513231349, https://openalex.org/W3103940881, https://openalex.org/W2167460663, https://openalex.org/W2048620831, https://openalex.org/W2962755762, https://openalex.org/W2144935315, https://openalex.org/W1495236921, https://openalex.org/W2257979135, https://openalex.org/W1593040460, https://openalex.org/W1538473628, https://openalex.org/W2914217871, https://openalex.org/W1968998685, https://openalex.org/W2167421362, https://openalex.org/W1966333039, https://openalex.org/W3091400502, https://openalex.org/W2157859776, https://openalex.org/W2133296809, https://openalex.org/W1540007258, https://openalex.org/W2399587145, https://openalex.org/W2096035548, https://openalex.org/W2102348129, https://openalex.org/W1594031697 |
| referenced_works_count | 45 |
| abstract_inverted_index.a | 71, 95, 133 |
| abstract_inverted_index.To | 63 |
| abstract_inverted_index.ad | 32 |
| abstract_inverted_index.by | 94 |
| abstract_inverted_index.in | 50, 83, 107, 201 |
| abstract_inverted_index.is | 12, 28, 105, 146 |
| abstract_inverted_index.of | 17, 80, 90, 100, 112, 180, 205 |
| abstract_inverted_index.on | 24, 31, 77, 138, 157 |
| abstract_inverted_index.or | 59 |
| abstract_inverted_index.to | 6, 13, 39, 55, 60, 124 |
| abstract_inverted_index.up | 123 |
| abstract_inverted_index.we | 168 |
| abstract_inverted_index.(i) | 171 |
| abstract_inverted_index.The | 98, 148 |
| abstract_inverted_index.and | 153, 184 |
| abstract_inverted_index.are | 4, 36, 53 |
| abstract_inverted_index.can | 119, 151, 176 |
| abstract_inverted_index.fly | 159 |
| abstract_inverted_index.for | 127 |
| abstract_inverted_index.hoc | 33 |
| abstract_inverted_index.our | 101 |
| abstract_inverted_index.the | 15, 18, 21, 45, 51, 78, 81, 85, 88, 110, 113, 116, 121, 128, 139, 158, 161, 172, 178, 187, 190, 203, 206 |
| abstract_inverted_index.two | 125 |
| abstract_inverted_index.(ii) | 185 |
| abstract_inverted_index.data | 7, 25, 47 |
| abstract_inverted_index.only | 37 |
| abstract_inverted_index.over | 109 |
| abstract_inverted_index.same | 129 |
| abstract_inverted_index.size | 111 |
| abstract_inverted_index.that | 35, 170 |
| abstract_inverted_index.this | 67 |
| abstract_inverted_index.time | 108 |
| abstract_inverted_index.Also, | 115 |
| abstract_inverted_index.based | 76, 137 |
| abstract_inverted_index.data, | 82 |
| abstract_inverted_index.error | 122 |
| abstract_inverted_index.first | 69 |
| abstract_inverted_index.model | 145 |
| abstract_inverted_index.novel | 72, 134 |
| abstract_inverted_index.other | 196 |
| abstract_inverted_index.paper | 68 |
| abstract_inverted_index.these | 65 |
| abstract_inverted_index.times | 126 |
| abstract_inverted_index.under | 186 |
| abstract_inverted_index.which | 84 |
| abstract_inverted_index.while | 92 |
| abstract_inverted_index.whose | 10 |
| abstract_inverted_index.(SRNN) | 144 |
| abstract_inverted_index.attack | 75, 103, 118, 130, 174 |
| abstract_inverted_index.binary | 57 |
| abstract_inverted_index.detect | 152 |
| abstract_inverted_index.during | 160 |
| abstract_inverted_index.either | 56 |
| abstract_inverted_index.linear | 106 |
| abstract_inverted_index.mainly | 29 |
| abstract_inverted_index.model. | 19, 208 |
| abstract_inverted_index.models | 3, 182, 200 |
| abstract_inverted_index.Nearest | 142 |
| abstract_inverted_index.Reduced | 141 |
| abstract_inverted_index.Second, | 132 |
| abstract_inverted_index.Through | 164 |
| abstract_inverted_index.address | 64 |
| abstract_inverted_index.attack, | 189 |
| abstract_inverted_index.attacks | 9, 27, 49 |
| abstract_inverted_index.budget. | 97, 131 |
| abstract_inverted_index.classes | 91 |
| abstract_inverted_index.current | 22 |
| abstract_inverted_index.defense | 135, 149, 192 |
| abstract_inverted_index.exclude | 154 |
| abstract_inverted_index.flipped | 155 |
| abstract_inverted_index.focused | 30 |
| abstract_inverted_index.limited | 54 |
| abstract_inverted_index.machine | 1, 41, 198 |
| abstract_inverted_index.models. | 43 |
| abstract_inverted_index.purpose | 11 |
| abstract_inverted_index.samples | 156 |
| abstract_inverted_index.several | 181 |
| abstract_inverted_index.targets | 87 |
| abstract_inverted_index.However, | 20 |
| abstract_inverted_index.Neighbor | 143 |
| abstract_inverted_index.accuracy | 179, 204 |
| abstract_inverted_index.clusters | 89 |
| abstract_inverted_index.dataset. | 114 |
| abstract_inverted_index.existing | 46 |
| abstract_inverted_index.increase | 120 |
| abstract_inverted_index.learning | 2, 42, 199 |
| abstract_inverted_index.proposed | 102, 117, 173, 188, 191 |
| abstract_inverted_index.proposes | 70 |
| abstract_inverted_index.specific | 40 |
| abstract_inverted_index.targeted | 207 |
| abstract_inverted_index.training | 162 |
| abstract_inverted_index.Synthetic | 140 |
| abstract_inverted_index.adversary | 86 |
| abstract_inverted_index.algorithm | 104 |
| abstract_inverted_index.analysis, | 167 |
| abstract_inverted_index.extensive | 165 |
| abstract_inverted_index.integrity | 16 |
| abstract_inverted_index.poisoning | 8, 26, 48 |
| abstract_inverted_index.proposed. | 147 |
| abstract_inverted_index.technique | 136, 150, 175, 193 |
| abstract_inverted_index.undermine | 14 |
| abstract_inverted_index.applicable | 38 |
| abstract_inverted_index.complexity | 99 |
| abstract_inverted_index.literature | 23, 52 |
| abstract_inverted_index.model-free | 73 |
| abstract_inverted_index.procedure. | 163 |
| abstract_inverted_index.recovering | 202 |
| abstract_inverted_index.techniques | 34 |
| abstract_inverted_index.vulnerable | 5 |
| abstract_inverted_index.algorithms. | 62 |
| abstract_inverted_index.classifiers | 58 |
| abstract_inverted_index.constrained | 93 |
| abstract_inverted_index.demonstrate | 169 |
| abstract_inverted_index.deteriorate | 177 |
| abstract_inverted_index.outperforms | 195 |
| abstract_inverted_index.conventional | 197 |
| abstract_inverted_index.drastically, | 183 |
| abstract_inverted_index.experimental | 166 |
| abstract_inverted_index.limitations, | 66 |
| abstract_inverted_index.Additionally, | 44 |
| abstract_inverted_index.significantly | 194 |
| abstract_inverted_index.gradient-based | 61 |
| abstract_inverted_index.label-flipping | 74, 96 |
| abstract_inverted_index.multi-modality | 79 |
| abstract_inverted_index.State-of-the-art | 0 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.41999998688697815 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile |