Depth-2 neural networks under a data-poisoning attack Article Swipe
Sayar Karmakar
,
Anirbit Mukherjee
,
Theodore Papamarkou
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1016/j.neucom.2023.02.034
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1016/j.neucom.2023.02.034
In this work, we study the possibility of defending against data-poisoning attacks while training a shallow neural network in a regression setup. We focus on doing supervised learning with realizable labels for a class of depth-2 finite-width neural networks, which includes single-filter convolutional networks. In this class of networks, we attempt to learn the true network weights generating the labels in the presence of a malicious oracle doing stochastic, bounded and additive adversarial distortions on the true labels, during training. For the gradient-free stochastic algorithm that we construct, we prove worst-case near-optimal trade-offs among the magnitude of the adversarial attack, the weight approximation accuracy, and the confidence achieved by the proposed algorithm. As our algorithm uses mini-batching, we analyze how the mini-batch size affects convergence. We also show how to utilize the scaling of the outer layer weights to counter data-poisoning attacks on true labels depending on the probability of attack. Lastly, we give experimental evidence demonstrating how our algorithm outperforms stochastic gradient descent under different input data distributions, including instances of heavy-tailed distributions.
Related Topics
Concepts
Computer science
Oracle
Stochastic gradient descent
Convergence (economics)
Bounded function
Focus (optics)
Artificial neural network
Construct (python library)
Convolutional neural network
Gradient descent
Filter (signal processing)
Algorithm
Artificial intelligence
Mathematics
Mathematical analysis
Programming language
Economics
Computer vision
Optics
Physics
Economic growth
Software engineering
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1016/j.neucom.2023.02.034
- OA Status
- hybrid
- Cited By
- 2
- References
- 40
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4321438945
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4321438945Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1016/j.neucom.2023.02.034Digital Object Identifier
- Title
-
Depth-2 neural networks under a data-poisoning attackWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-02-21Full publication date if available
- Authors
-
Sayar Karmakar, Anirbit Mukherjee, Theodore PapamarkouList of authors in order
- Landing page
-
https://doi.org/10.1016/j.neucom.2023.02.034Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1016/j.neucom.2023.02.034Direct OA link when available
- Concepts
-
Computer science, Oracle, Stochastic gradient descent, Convergence (economics), Bounded function, Focus (optics), Artificial neural network, Construct (python library), Convolutional neural network, Gradient descent, Filter (signal processing), Algorithm, Artificial intelligence, Mathematics, Mathematical analysis, Programming language, Economics, Computer vision, Optics, Physics, Economic growth, Software engineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 2Per-year citation counts (last 5 years)
- References (count)
-
40Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4321438945 |
|---|---|
| doi | https://doi.org/10.1016/j.neucom.2023.02.034 |
| ids.doi | https://doi.org/10.1016/j.neucom.2023.02.034 |
| ids.openalex | https://openalex.org/W4321438945 |
| fwci | 0.51088578 |
| type | article |
| title | Depth-2 neural networks under a data-poisoning attack |
| biblio.issue | |
| biblio.volume | 532 |
| biblio.last_page | 66 |
| biblio.first_page | 56 |
| 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 | 1.0 |
| 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/T11307 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9714000225067139 |
| 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 | Domain Adaptation and Few-Shot Learning |
| topics[2].id | https://openalex.org/T11512 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9695000052452087 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Anomaly Detection Techniques and Applications |
| is_xpac | False |
| apc_list.value | 2470 |
| apc_list.currency | USD |
| apc_list.value_usd | 2470 |
| apc_paid.value | 2470 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 2470 |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7066951394081116 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C55166926 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6611658930778503 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2892946 |
| concepts[1].display_name | Oracle |
| concepts[2].id | https://openalex.org/C206688291 |
| concepts[2].level | 3 |
| concepts[2].score | 0.6315523386001587 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q7617819 |
| concepts[2].display_name | Stochastic gradient descent |
| concepts[3].id | https://openalex.org/C2777303404 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5994251370429993 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q759757 |
| concepts[3].display_name | Convergence (economics) |
| concepts[4].id | https://openalex.org/C34388435 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5651963353157043 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2267362 |
| concepts[4].display_name | Bounded function |
| concepts[5].id | https://openalex.org/C192209626 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5448042154312134 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q190909 |
| concepts[5].display_name | Focus (optics) |
| concepts[6].id | https://openalex.org/C50644808 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5339184403419495 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[6].display_name | Artificial neural network |
| concepts[7].id | https://openalex.org/C2780801425 |
| concepts[7].level | 2 |
| concepts[7].score | 0.503511369228363 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q5164392 |
| concepts[7].display_name | Construct (python library) |
| concepts[8].id | https://openalex.org/C81363708 |
| concepts[8].level | 2 |
| concepts[8].score | 0.49250754714012146 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[8].display_name | Convolutional neural network |
| concepts[9].id | https://openalex.org/C153258448 |
| concepts[9].level | 3 |
| concepts[9].score | 0.46627262234687805 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1199743 |
| concepts[9].display_name | Gradient descent |
| concepts[10].id | https://openalex.org/C106131492 |
| concepts[10].level | 2 |
| concepts[10].score | 0.4601178467273712 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q3072260 |
| concepts[10].display_name | Filter (signal processing) |
| concepts[11].id | https://openalex.org/C11413529 |
| concepts[11].level | 1 |
| concepts[11].score | 0.45358139276504517 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[11].display_name | Algorithm |
| concepts[12].id | https://openalex.org/C154945302 |
| concepts[12].level | 1 |
| concepts[12].score | 0.44108232855796814 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[12].display_name | Artificial intelligence |
| concepts[13].id | https://openalex.org/C33923547 |
| concepts[13].level | 0 |
| concepts[13].score | 0.21996212005615234 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[13].display_name | Mathematics |
| concepts[14].id | https://openalex.org/C134306372 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[14].display_name | Mathematical analysis |
| concepts[15].id | https://openalex.org/C199360897 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[15].display_name | Programming language |
| concepts[16].id | https://openalex.org/C162324750 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[16].display_name | Economics |
| concepts[17].id | https://openalex.org/C31972630 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[17].display_name | Computer vision |
| concepts[18].id | https://openalex.org/C120665830 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q14620 |
| concepts[18].display_name | Optics |
| concepts[19].id | https://openalex.org/C121332964 |
| concepts[19].level | 0 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[19].display_name | Physics |
| concepts[20].id | https://openalex.org/C50522688 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q189833 |
| concepts[20].display_name | Economic growth |
| concepts[21].id | https://openalex.org/C115903868 |
| concepts[21].level | 1 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q80993 |
| concepts[21].display_name | Software engineering |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7066951394081116 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/oracle |
| keywords[1].score | 0.6611658930778503 |
| keywords[1].display_name | Oracle |
| keywords[2].id | https://openalex.org/keywords/stochastic-gradient-descent |
| keywords[2].score | 0.6315523386001587 |
| keywords[2].display_name | Stochastic gradient descent |
| keywords[3].id | https://openalex.org/keywords/convergence |
| keywords[3].score | 0.5994251370429993 |
| keywords[3].display_name | Convergence (economics) |
| keywords[4].id | https://openalex.org/keywords/bounded-function |
| keywords[4].score | 0.5651963353157043 |
| keywords[4].display_name | Bounded function |
| keywords[5].id | https://openalex.org/keywords/focus |
| keywords[5].score | 0.5448042154312134 |
| keywords[5].display_name | Focus (optics) |
| keywords[6].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[6].score | 0.5339184403419495 |
| keywords[6].display_name | Artificial neural network |
| keywords[7].id | https://openalex.org/keywords/construct |
| keywords[7].score | 0.503511369228363 |
| keywords[7].display_name | Construct (python library) |
| keywords[8].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[8].score | 0.49250754714012146 |
| keywords[8].display_name | Convolutional neural network |
| keywords[9].id | https://openalex.org/keywords/gradient-descent |
| keywords[9].score | 0.46627262234687805 |
| keywords[9].display_name | Gradient descent |
| keywords[10].id | https://openalex.org/keywords/filter |
| keywords[10].score | 0.4601178467273712 |
| keywords[10].display_name | Filter (signal processing) |
| keywords[11].id | https://openalex.org/keywords/algorithm |
| keywords[11].score | 0.45358139276504517 |
| keywords[11].display_name | Algorithm |
| keywords[12].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[12].score | 0.44108232855796814 |
| keywords[12].display_name | Artificial intelligence |
| keywords[13].id | https://openalex.org/keywords/mathematics |
| keywords[13].score | 0.21996212005615234 |
| keywords[13].display_name | Mathematics |
| language | en |
| locations[0].id | doi:10.1016/j.neucom.2023.02.034 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S45693802 |
| locations[0].source.issn | 0925-2312, 1872-8286 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 0925-2312 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Neurocomputing |
| locations[0].source.host_organization | https://openalex.org/P4310320990 |
| locations[0].source.host_organization_name | Elsevier BV |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320990 |
| locations[0].source.host_organization_lineage_names | Elsevier BV |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| 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 | Neurocomputing |
| locations[0].landing_page_url | https://doi.org/10.1016/j.neucom.2023.02.034 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5083218909 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-4841-2069 |
| authorships[0].author.display_name | Sayar Karmakar |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I33213144 |
| authorships[0].affiliations[0].raw_affiliation_string | Department of Statistics, University of Florida, 230 Newell Drive, Gainesville 32611, FL, USA |
| authorships[0].institutions[0].id | https://openalex.org/I33213144 |
| authorships[0].institutions[0].ror | https://ror.org/02y3ad647 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I33213144 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | University of Florida |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Sayar Karmakar |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Department of Statistics, University of Florida, 230 Newell Drive, Gainesville 32611, FL, USA |
| authorships[1].author.id | https://openalex.org/A5084835559 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5189-8939 |
| authorships[1].author.display_name | Anirbit Mukherjee |
| authorships[1].countries | GB |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I28407311 |
| authorships[1].affiliations[0].raw_affiliation_string | Department of Computer Science, The University of Manchester, Kilburn Building, Oxford Road, Manchester M139PL, UK |
| authorships[1].institutions[0].id | https://openalex.org/I28407311 |
| authorships[1].institutions[0].ror | https://ror.org/027m9bs27 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I28407311 |
| authorships[1].institutions[0].country_code | GB |
| authorships[1].institutions[0].display_name | University of Manchester |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Anirbit Mukherjee |
| authorships[1].is_corresponding | True |
| authorships[1].raw_affiliation_strings | Department of Computer Science, The University of Manchester, Kilburn Building, Oxford Road, Manchester M139PL, UK |
| authorships[2].author.id | https://openalex.org/A5080301618 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-9689-543X |
| authorships[2].author.display_name | Theodore Papamarkou |
| authorships[2].countries | GB |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I28407311 |
| authorships[2].affiliations[0].raw_affiliation_string | Department of Mathematics, The University of Manchester, Alan Turing Building, Oxford Road, Manchester M13 9PL, UK |
| authorships[2].institutions[0].id | https://openalex.org/I28407311 |
| authorships[2].institutions[0].ror | https://ror.org/027m9bs27 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I28407311 |
| authorships[2].institutions[0].country_code | GB |
| authorships[2].institutions[0].display_name | University of Manchester |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Theodore Papamarkou |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Department of Mathematics, The University of Manchester, Alan Turing Building, Oxford Road, Manchester M13 9PL, UK |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1016/j.neucom.2023.02.034 |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Depth-2 neural networks under a data-poisoning attack |
| 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 | 1.0 |
| 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/W2895097035, https://openalex.org/W4206903459, https://openalex.org/W2754816816, https://openalex.org/W4366280654, https://openalex.org/W3160167280, https://openalex.org/W4362706668, https://openalex.org/W4231621013, https://openalex.org/W3171021120, https://openalex.org/W3008318776, https://openalex.org/W2041416246 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 2 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1016/j.neucom.2023.02.034 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S45693802 |
| best_oa_location.source.issn | 0925-2312, 1872-8286 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 0925-2312 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Neurocomputing |
| best_oa_location.source.host_organization | https://openalex.org/P4310320990 |
| best_oa_location.source.host_organization_name | Elsevier BV |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320990 |
| best_oa_location.source.host_organization_lineage_names | Elsevier BV |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| 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 | Neurocomputing |
| best_oa_location.landing_page_url | https://doi.org/10.1016/j.neucom.2023.02.034 |
| primary_location.id | doi:10.1016/j.neucom.2023.02.034 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S45693802 |
| primary_location.source.issn | 0925-2312, 1872-8286 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 0925-2312 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Neurocomputing |
| primary_location.source.host_organization | https://openalex.org/P4310320990 |
| primary_location.source.host_organization_name | Elsevier BV |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320990 |
| primary_location.source.host_organization_lineage_names | Elsevier BV |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| 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 | Neurocomputing |
| primary_location.landing_page_url | https://doi.org/10.1016/j.neucom.2023.02.034 |
| publication_date | 2023-02-21 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W2603766943, https://openalex.org/W6731685432, https://openalex.org/W6600599538, https://openalex.org/W2962700793, https://openalex.org/W2919491917, https://openalex.org/W6600263792, https://openalex.org/W6600883950, https://openalex.org/W6635264123, https://openalex.org/W6630022845, https://openalex.org/W6600339963, https://openalex.org/W6600020652, https://openalex.org/W6779272815, https://openalex.org/W2040870580, https://openalex.org/W2095727900, https://openalex.org/W4249572517, https://openalex.org/W6754539863, https://openalex.org/W6739227815, https://openalex.org/W6601651114, https://openalex.org/W6752073087, https://openalex.org/W6699755906, https://openalex.org/W6681673350, https://openalex.org/W6600679772, https://openalex.org/W6742291808, https://openalex.org/W6713228291, https://openalex.org/W6758684365, https://openalex.org/W6773640337, https://openalex.org/W2962763344, https://openalex.org/W6600376255, https://openalex.org/W6601955380, https://openalex.org/W6604197512, https://openalex.org/W2767023880, https://openalex.org/W2962909343, https://openalex.org/W2161310686, https://openalex.org/W6631374731, https://openalex.org/W6606580801, https://openalex.org/W6760993166, https://openalex.org/W2125908420, https://openalex.org/W4223985028, https://openalex.org/W6605898172, https://openalex.org/W4298844065 |
| referenced_works_count | 40 |
| abstract_inverted_index.a | 14, 19, 32, 64 |
| abstract_inverted_index.As | 112 |
| abstract_inverted_index.In | 0, 44 |
| abstract_inverted_index.We | 22, 125 |
| abstract_inverted_index.by | 108 |
| abstract_inverted_index.in | 18, 60 |
| abstract_inverted_index.of | 7, 34, 47, 63, 96, 133, 149, 171 |
| abstract_inverted_index.on | 24, 74, 142, 146 |
| abstract_inverted_index.to | 51, 129, 138 |
| abstract_inverted_index.we | 3, 49, 86, 88, 117, 152 |
| abstract_inverted_index.For | 80 |
| abstract_inverted_index.and | 70, 104 |
| abstract_inverted_index.for | 31 |
| abstract_inverted_index.how | 119, 128, 157 |
| abstract_inverted_index.our | 113, 158 |
| abstract_inverted_index.the | 5, 53, 58, 61, 75, 81, 94, 97, 100, 105, 109, 120, 131, 134, 147 |
| abstract_inverted_index.also | 126 |
| abstract_inverted_index.data | 167 |
| abstract_inverted_index.give | 153 |
| abstract_inverted_index.show | 127 |
| abstract_inverted_index.size | 122 |
| abstract_inverted_index.that | 85 |
| abstract_inverted_index.this | 1, 45 |
| abstract_inverted_index.true | 54, 76, 143 |
| abstract_inverted_index.uses | 115 |
| abstract_inverted_index.with | 28 |
| abstract_inverted_index.among | 93 |
| abstract_inverted_index.class | 33, 46 |
| abstract_inverted_index.doing | 25, 67 |
| abstract_inverted_index.focus | 23 |
| abstract_inverted_index.input | 166 |
| abstract_inverted_index.layer | 136 |
| abstract_inverted_index.learn | 52 |
| abstract_inverted_index.outer | 135 |
| abstract_inverted_index.prove | 89 |
| abstract_inverted_index.study | 4 |
| abstract_inverted_index.under | 164 |
| abstract_inverted_index.which | 39 |
| abstract_inverted_index.while | 12 |
| abstract_inverted_index.work, | 2 |
| abstract_inverted_index.during | 78 |
| abstract_inverted_index.labels | 30, 59, 144 |
| abstract_inverted_index.neural | 16, 37 |
| abstract_inverted_index.oracle | 66 |
| abstract_inverted_index.setup. | 21 |
| abstract_inverted_index.weight | 101 |
| abstract_inverted_index.Lastly, | 151 |
| abstract_inverted_index.affects | 123 |
| abstract_inverted_index.against | 9 |
| abstract_inverted_index.analyze | 118 |
| abstract_inverted_index.attack, | 99 |
| abstract_inverted_index.attack. | 150 |
| abstract_inverted_index.attacks | 11, 141 |
| abstract_inverted_index.attempt | 50 |
| abstract_inverted_index.bounded | 69 |
| abstract_inverted_index.counter | 139 |
| abstract_inverted_index.depth-2 | 35 |
| abstract_inverted_index.descent | 163 |
| abstract_inverted_index.labels, | 77 |
| abstract_inverted_index.network | 17, 55 |
| abstract_inverted_index.scaling | 132 |
| abstract_inverted_index.shallow | 15 |
| abstract_inverted_index.utilize | 130 |
| abstract_inverted_index.weights | 56, 137 |
| abstract_inverted_index.achieved | 107 |
| abstract_inverted_index.additive | 71 |
| abstract_inverted_index.evidence | 155 |
| abstract_inverted_index.gradient | 162 |
| abstract_inverted_index.includes | 40 |
| abstract_inverted_index.learning | 27 |
| abstract_inverted_index.presence | 62 |
| abstract_inverted_index.proposed | 110 |
| abstract_inverted_index.training | 13 |
| abstract_inverted_index.accuracy, | 103 |
| abstract_inverted_index.algorithm | 84, 114, 159 |
| abstract_inverted_index.defending | 8 |
| abstract_inverted_index.depending | 145 |
| abstract_inverted_index.different | 165 |
| abstract_inverted_index.including | 169 |
| abstract_inverted_index.instances | 170 |
| abstract_inverted_index.magnitude | 95 |
| abstract_inverted_index.malicious | 65 |
| abstract_inverted_index.networks, | 38, 48 |
| abstract_inverted_index.networks. | 43 |
| abstract_inverted_index.training. | 79 |
| abstract_inverted_index.algorithm. | 111 |
| abstract_inverted_index.confidence | 106 |
| abstract_inverted_index.construct, | 87 |
| abstract_inverted_index.generating | 57 |
| abstract_inverted_index.mini-batch | 121 |
| abstract_inverted_index.realizable | 29 |
| abstract_inverted_index.regression | 20 |
| abstract_inverted_index.stochastic | 83, 161 |
| abstract_inverted_index.supervised | 26 |
| abstract_inverted_index.trade-offs | 92 |
| abstract_inverted_index.worst-case | 90 |
| abstract_inverted_index.adversarial | 72, 98 |
| abstract_inverted_index.distortions | 73 |
| abstract_inverted_index.outperforms | 160 |
| abstract_inverted_index.possibility | 6 |
| abstract_inverted_index.probability | 148 |
| abstract_inverted_index.stochastic, | 68 |
| abstract_inverted_index.convergence. | 124 |
| abstract_inverted_index.experimental | 154 |
| abstract_inverted_index.finite-width | 36 |
| abstract_inverted_index.heavy-tailed | 172 |
| abstract_inverted_index.near-optimal | 91 |
| abstract_inverted_index.approximation | 102 |
| abstract_inverted_index.convolutional | 42 |
| abstract_inverted_index.demonstrating | 156 |
| abstract_inverted_index.gradient-free | 82 |
| abstract_inverted_index.single-filter | 41 |
| abstract_inverted_index.data-poisoning | 10, 140 |
| abstract_inverted_index.distributions, | 168 |
| abstract_inverted_index.distributions. | 173 |
| abstract_inverted_index.mini-batching, | 116 |
| cited_by_percentile_year.max | 96 |
| cited_by_percentile_year.min | 94 |
| corresponding_author_ids | https://openalex.org/A5084835559 |
| countries_distinct_count | 2 |
| institutions_distinct_count | 3 |
| corresponding_institution_ids | https://openalex.org/I28407311 |
| citation_normalized_percentile.value | 0.64638495 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |