Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks Article Swipe
Despite the widespread use of machine learning in adversarial settings such as computer security, recent studies have demonstrated vulnerabilities to evasion attacks—carefully crafted adversarial samples that closely resemble legitimate instances, but cause misclassification. In this paper, we examine\nthe adequacy of the leading approach to generating adversarial samples—the gradient-descent approach. In particular (1) we perform extensive experiments on three datasets, MNIST, USPS and Spambase, in order to analyse the effectiveness of the gradient-descent method against non-linear support vector machines, and conclude that carefully reduced kernel smoothness can significantly increase robustness to the attack; (2) we demonstrate that separated inter-class support vectors lead to more secure models, and propose a quantity similar to margin that can efficiently predict potential susceptibility to gradient-descent attacks, before the attack is launched; and (3) we design a new adversarial sample construction algorithm based on optimising the multiplicative ratio of class decision functions.
Related Topics
Concepts
Gradient descent
Computer science
MNIST database
Adversarial system
Support vector machine
Artificial intelligence
Machine learning
Classifier (UML)
Multiplicative function
Robustness (evolution)
Adversarial machine learning
Pattern recognition (psychology)
Deep learning
Artificial neural network
Mathematics
Gene
Chemistry
Biochemistry
Mathematical analysis
Metadata
- Type
- article
- Language
- en
- Landing Page
- http://hdl.handle.net/11343/211676
- OA Status
- green
- Cited By
- 2
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W2964211224
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W2964211224Canonical identifier for this work in OpenAlex
- Title
-
Adequacy of the Gradient-Descent Method for Classifier Evasion AttacksWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2018Year of publication
- Publication date
-
2018-01-01Full publication date if available
- Authors
-
Yi Han, Benjamin I. P. RubinsteinList of authors in order
- Landing page
-
https://hdl.handle.net/11343/211676Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/abs/1704.01704Direct OA link when available
- Concepts
-
Gradient descent, Computer science, MNIST database, Adversarial system, Support vector machine, Artificial intelligence, Machine learning, Classifier (UML), Multiplicative function, Robustness (evolution), Adversarial machine learning, Pattern recognition (psychology), Deep learning, Artificial neural network, Mathematics, Gene, Chemistry, Biochemistry, Mathematical analysisTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2021: 1, 2019: 1Per-year citation counts (last 5 years)
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W2964211224 |
|---|---|
| doi | |
| ids.mag | 2964211224 |
| ids.openalex | https://openalex.org/W2964211224 |
| fwci | 0.39712492 |
| type | article |
| title | Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 244 |
| biblio.first_page | 237 |
| 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 | 0.9988999962806702 |
| 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/T11515 |
| topics[1].field.id | https://openalex.org/fields/13 |
| topics[1].field.display_name | Biochemistry, Genetics and Molecular Biology |
| topics[1].score | 0.9476000070571899 |
| topics[1].domain.id | https://openalex.org/domains/1 |
| topics[1].domain.display_name | Life Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1312 |
| topics[1].subfield.display_name | Molecular Biology |
| topics[1].display_name | Bacillus and Francisella bacterial research |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C153258448 |
| concepts[0].level | 3 |
| concepts[0].score | 0.7296429872512817 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1199743 |
| concepts[0].display_name | Gradient descent |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6897056102752686 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C190502265 |
| concepts[2].level | 3 |
| concepts[2].score | 0.6027555465698242 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17069496 |
| concepts[2].display_name | MNIST database |
| concepts[3].id | https://openalex.org/C37736160 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5929276347160339 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[3].display_name | Adversarial system |
| concepts[4].id | https://openalex.org/C12267149 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5859435796737671 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q282453 |
| concepts[4].display_name | Support vector machine |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5474532246589661 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.4932364821434021 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C95623464 |
| concepts[7].level | 2 |
| concepts[7].score | 0.44723349809646606 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1096149 |
| concepts[7].display_name | Classifier (UML) |
| concepts[8].id | https://openalex.org/C42747912 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4455561637878418 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q1048447 |
| concepts[8].display_name | Multiplicative function |
| concepts[9].id | https://openalex.org/C63479239 |
| concepts[9].level | 3 |
| concepts[9].score | 0.4256938397884369 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[9].display_name | Robustness (evolution) |
| concepts[10].id | https://openalex.org/C2778403875 |
| concepts[10].level | 3 |
| concepts[10].score | 0.4243174195289612 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q20312394 |
| concepts[10].display_name | Adversarial machine learning |
| concepts[11].id | https://openalex.org/C153180895 |
| concepts[11].level | 2 |
| concepts[11].score | 0.36829498410224915 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[11].display_name | Pattern recognition (psychology) |
| concepts[12].id | https://openalex.org/C108583219 |
| concepts[12].level | 2 |
| concepts[12].score | 0.19163814187049866 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[12].display_name | Deep learning |
| concepts[13].id | https://openalex.org/C50644808 |
| concepts[13].level | 2 |
| concepts[13].score | 0.17748594284057617 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[13].display_name | Artificial neural network |
| concepts[14].id | https://openalex.org/C33923547 |
| concepts[14].level | 0 |
| concepts[14].score | 0.15684345364570618 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[14].display_name | Mathematics |
| concepts[15].id | https://openalex.org/C104317684 |
| concepts[15].level | 2 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[15].display_name | Gene |
| concepts[16].id | https://openalex.org/C185592680 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[16].display_name | Chemistry |
| concepts[17].id | https://openalex.org/C55493867 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[17].display_name | Biochemistry |
| concepts[18].id | https://openalex.org/C134306372 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[18].display_name | Mathematical analysis |
| keywords[0].id | https://openalex.org/keywords/gradient-descent |
| keywords[0].score | 0.7296429872512817 |
| keywords[0].display_name | Gradient descent |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6897056102752686 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/mnist-database |
| keywords[2].score | 0.6027555465698242 |
| keywords[2].display_name | MNIST database |
| keywords[3].id | https://openalex.org/keywords/adversarial-system |
| keywords[3].score | 0.5929276347160339 |
| keywords[3].display_name | Adversarial system |
| keywords[4].id | https://openalex.org/keywords/support-vector-machine |
| keywords[4].score | 0.5859435796737671 |
| keywords[4].display_name | Support vector machine |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.5474532246589661 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.4932364821434021 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/classifier |
| keywords[7].score | 0.44723349809646606 |
| keywords[7].display_name | Classifier (UML) |
| keywords[8].id | https://openalex.org/keywords/multiplicative-function |
| keywords[8].score | 0.4455561637878418 |
| keywords[8].display_name | Multiplicative function |
| keywords[9].id | https://openalex.org/keywords/robustness |
| keywords[9].score | 0.4256938397884369 |
| keywords[9].display_name | Robustness (evolution) |
| keywords[10].id | https://openalex.org/keywords/adversarial-machine-learning |
| keywords[10].score | 0.4243174195289612 |
| keywords[10].display_name | Adversarial machine learning |
| keywords[11].id | https://openalex.org/keywords/pattern-recognition |
| keywords[11].score | 0.36829498410224915 |
| keywords[11].display_name | Pattern recognition (psychology) |
| keywords[12].id | https://openalex.org/keywords/deep-learning |
| keywords[12].score | 0.19163814187049866 |
| keywords[12].display_name | Deep learning |
| keywords[13].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[13].score | 0.17748594284057617 |
| keywords[13].display_name | Artificial neural network |
| keywords[14].id | https://openalex.org/keywords/mathematics |
| keywords[14].score | 0.15684345364570618 |
| keywords[14].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:jupiter.its.unimelb.edu.au:11343/211676 |
| locations[0].is_oa | False |
| locations[0].source.id | https://openalex.org/S4306402500 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Minerva Access (University of Melbourne) |
| locations[0].source.host_organization | https://openalex.org/I165779595 |
| locations[0].source.host_organization_name | University of Melbourne |
| locations[0].source.host_organization_lineage | https://openalex.org/I165779595 |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | submittedVersion |
| locations[0].raw_type | Conference Paper |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | The AAAI-18 Workshop on Artificial Intelligence for Cyber Security |
| locations[0].landing_page_url | http://hdl.handle.net/11343/211676 |
| locations[1].id | mag:2964211224 |
| 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 | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | arXiv (Cornell University) |
| locations[1].landing_page_url | https://arxiv.org/abs/1704.01704 |
| authorships[0].author.id | https://openalex.org/A5020908862 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-6530-4564 |
| authorships[0].author.display_name | Yi Han |
| authorships[0].countries | AU |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I165779595 |
| authorships[0].affiliations[0].raw_affiliation_string | University of Melbourne, Melbourne, Australia |
| authorships[0].institutions[0].id | https://openalex.org/I165779595 |
| authorships[0].institutions[0].ror | https://ror.org/01ej9dk98 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I165779595 |
| authorships[0].institutions[0].country_code | AU |
| authorships[0].institutions[0].display_name | The University of Melbourne |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yi Han |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | University of Melbourne, Melbourne, Australia |
| authorships[1].author.id | https://openalex.org/A5078824132 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-2947-6980 |
| authorships[1].author.display_name | Benjamin I. P. Rubinstein |
| authorships[1].countries | AU |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I165779595 |
| authorships[1].affiliations[0].raw_affiliation_string | University of Melbourne, Melbourne, Australia |
| authorships[1].institutions[0].id | https://openalex.org/I165779595 |
| authorships[1].institutions[0].ror | https://ror.org/01ej9dk98 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I165779595 |
| authorships[1].institutions[0].country_code | AU |
| authorships[1].institutions[0].display_name | The University of Melbourne |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Benjamin I. P. Rubinstein |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | University of Melbourne, Melbourne, Australia |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/abs/1704.01704 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-10-10T17:16:08.811792 |
| 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 | 0.9988999962806702 |
| 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/W2605658383, https://openalex.org/W3109751798, https://openalex.org/W3128513745, https://openalex.org/W3196460263, https://openalex.org/W3120578866, https://openalex.org/W3211686381, https://openalex.org/W3015424723, https://openalex.org/W3161752261, https://openalex.org/W3094378214, https://openalex.org/W2803678876, https://openalex.org/W3037085720, https://openalex.org/W3086146226, https://openalex.org/W2904294250, https://openalex.org/W3174528043, https://openalex.org/W3011700838, https://openalex.org/W2997674698, https://openalex.org/W2963539306, https://openalex.org/W2948318201, https://openalex.org/W2988677439, https://openalex.org/W2996344901 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2021 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2019 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | mag:2964211224 |
| 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 | |
| best_oa_location.version | |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | arXiv (Cornell University) |
| best_oa_location.landing_page_url | https://arxiv.org/abs/1704.01704 |
| primary_location.id | pmh:oai:jupiter.its.unimelb.edu.au:11343/211676 |
| primary_location.is_oa | False |
| primary_location.source.id | https://openalex.org/S4306402500 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Minerva Access (University of Melbourne) |
| primary_location.source.host_organization | https://openalex.org/I165779595 |
| primary_location.source.host_organization_name | University of Melbourne |
| primary_location.source.host_organization_lineage | https://openalex.org/I165779595 |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | submittedVersion |
| primary_location.raw_type | Conference Paper |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | The AAAI-18 Workshop on Artificial Intelligence for Cyber Security |
| primary_location.landing_page_url | http://hdl.handle.net/11343/211676 |
| publication_date | 2018-01-01 |
| publication_year | 2018 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 107, 130 |
| abstract_inverted_index.In | 33, 49 |
| abstract_inverted_index.as | 11 |
| abstract_inverted_index.in | 7, 63 |
| abstract_inverted_index.is | 124 |
| abstract_inverted_index.of | 4, 39, 69, 142 |
| abstract_inverted_index.on | 56, 137 |
| abstract_inverted_index.to | 19, 43, 65, 89, 101, 110, 118 |
| abstract_inverted_index.we | 36, 52, 93, 128 |
| abstract_inverted_index.(1) | 51 |
| abstract_inverted_index.(2) | 92 |
| abstract_inverted_index.(3) | 127 |
| abstract_inverted_index.and | 61, 78, 105, 126 |
| abstract_inverted_index.but | 30 |
| abstract_inverted_index.can | 85, 113 |
| abstract_inverted_index.new | 131 |
| abstract_inverted_index.the | 1, 40, 67, 70, 90, 122, 139 |
| abstract_inverted_index.use | 3 |
| abstract_inverted_index.USPS | 60 |
| abstract_inverted_index.have | 16 |
| abstract_inverted_index.lead | 100 |
| abstract_inverted_index.more | 102 |
| abstract_inverted_index.such | 10 |
| abstract_inverted_index.that | 25, 80, 95, 112 |
| abstract_inverted_index.this | 34 |
| abstract_inverted_index.based | 136 |
| abstract_inverted_index.cause | 31 |
| abstract_inverted_index.class | 143 |
| abstract_inverted_index.order | 64 |
| abstract_inverted_index.ratio | 141 |
| abstract_inverted_index.three | 57 |
| abstract_inverted_index.MNIST, | 59 |
| abstract_inverted_index.attack | 123 |
| abstract_inverted_index.before | 121 |
| abstract_inverted_index.design | 129 |
| abstract_inverted_index.kernel | 83 |
| abstract_inverted_index.margin | 111 |
| abstract_inverted_index.method | 72 |
| abstract_inverted_index.paper, | 35 |
| abstract_inverted_index.recent | 14 |
| abstract_inverted_index.sample | 133 |
| abstract_inverted_index.secure | 103 |
| abstract_inverted_index.vector | 76 |
| abstract_inverted_index.Despite | 0 |
| abstract_inverted_index.against | 73 |
| abstract_inverted_index.analyse | 66 |
| abstract_inverted_index.attack; | 91 |
| abstract_inverted_index.closely | 26 |
| abstract_inverted_index.crafted | 22 |
| abstract_inverted_index.evasion | 20 |
| abstract_inverted_index.leading | 41 |
| abstract_inverted_index.machine | 5 |
| abstract_inverted_index.models, | 104 |
| abstract_inverted_index.perform | 53 |
| abstract_inverted_index.predict | 115 |
| abstract_inverted_index.propose | 106 |
| abstract_inverted_index.reduced | 82 |
| abstract_inverted_index.samples | 24 |
| abstract_inverted_index.similar | 109 |
| abstract_inverted_index.studies | 15 |
| abstract_inverted_index.support | 75, 98 |
| abstract_inverted_index.vectors | 99 |
| abstract_inverted_index.adequacy | 38 |
| abstract_inverted_index.approach | 42 |
| abstract_inverted_index.attacks, | 120 |
| abstract_inverted_index.computer | 12 |
| abstract_inverted_index.conclude | 79 |
| abstract_inverted_index.decision | 144 |
| abstract_inverted_index.increase | 87 |
| abstract_inverted_index.learning | 6 |
| abstract_inverted_index.quantity | 108 |
| abstract_inverted_index.resemble | 27 |
| abstract_inverted_index.settings | 9 |
| abstract_inverted_index.Spambase, | 62 |
| abstract_inverted_index.algorithm | 135 |
| abstract_inverted_index.approach. | 48 |
| abstract_inverted_index.carefully | 81 |
| abstract_inverted_index.datasets, | 58 |
| abstract_inverted_index.extensive | 54 |
| abstract_inverted_index.launched; | 125 |
| abstract_inverted_index.machines, | 77 |
| abstract_inverted_index.potential | 116 |
| abstract_inverted_index.security, | 13 |
| abstract_inverted_index.separated | 96 |
| abstract_inverted_index.functions. | 145 |
| abstract_inverted_index.generating | 44 |
| abstract_inverted_index.instances, | 29 |
| abstract_inverted_index.legitimate | 28 |
| abstract_inverted_index.non-linear | 74 |
| abstract_inverted_index.optimising | 138 |
| abstract_inverted_index.particular | 50 |
| abstract_inverted_index.robustness | 88 |
| abstract_inverted_index.smoothness | 84 |
| abstract_inverted_index.widespread | 2 |
| abstract_inverted_index.adversarial | 8, 23, 45, 132 |
| abstract_inverted_index.demonstrate | 94 |
| abstract_inverted_index.efficiently | 114 |
| abstract_inverted_index.experiments | 55 |
| abstract_inverted_index.inter-class | 97 |
| abstract_inverted_index.construction | 134 |
| abstract_inverted_index.demonstrated | 17 |
| abstract_inverted_index.examine\nthe | 37 |
| abstract_inverted_index.effectiveness | 68 |
| abstract_inverted_index.samples—the | 46 |
| abstract_inverted_index.significantly | 86 |
| abstract_inverted_index.multiplicative | 140 |
| abstract_inverted_index.susceptibility | 117 |
| abstract_inverted_index.vulnerabilities | 18 |
| abstract_inverted_index.gradient-descent | 47, 71, 119 |
| abstract_inverted_index.misclassification. | 32 |
| abstract_inverted_index.attacks—carefully | 21 |
| cited_by_percentile_year.max | 94 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 2 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.6700000166893005 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile.value | 0.70816857 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |