HarDNN: Feature Map Vulnerability Evaluation in CNNs Article Swipe
Abdulrahman Mahmoud
,
Siva Kumar Sastry Hari
,
Christopher W. Fletcher
,
Sarita V. Adve
,
Charbel Sakr
,
Naresh R. Shanbhag
,
Pavlo Molchanov
,
Michael B. Sullivan
,
Timothy Tsai
,
Stephen W. Keckler
·
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2002.09786
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2002.09786
As Convolutional Neural Networks (CNNs) are increasingly being employed in safety-critical applications, it is important that they behave reliably in the face of hardware errors. Transient hardware errors may percolate undesirable state during execution, resulting in software-manifested errors which can adversely affect high-level decision making. This paper presents HarDNN, a software-directed approach to identify vulnerable computations during a CNN inference and selectively protect them based on their propensity towards corrupting the inference output in the presence of a hardware error. We show that HarDNN can accurately estimate relative vulnerability of a feature map (fmap) in CNNs using a statistical error injection campaign, and explore heuristics for fast vulnerability assessment. Based on these results, we analyze the tradeoff between error coverage and computational overhead that the system designers can use to employ selective protection. Results show that the improvement in resilience for the added computation is superlinear with HarDNN. For example, HarDNN improves SqueezeNet's resilience by 10x with just 30% additional computations.
Related Topics
Concepts
Computer science
Heuristics
Convolutional neural network
Vulnerability (computing)
Overhead (engineering)
Computation
Resilience (materials science)
Inference
Feature (linguistics)
Software
Computer engineering
Artificial intelligence
Machine learning
Real-time computing
Data mining
Pattern recognition (psychology)
Algorithm
Computer security
Linguistics
Programming language
Thermodynamics
Philosophy
Operating system
Physics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2002.09786
- https://arxiv.org/pdf/2002.09786
- OA Status
- green
- Cited By
- 12
- References
- 26
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3008300587
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3008300587Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2002.09786Digital Object Identifier
- Title
-
HarDNN: Feature Map Vulnerability Evaluation in CNNsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2020Year of publication
- Publication date
-
2020-02-22Full publication date if available
- Authors
-
Abdulrahman Mahmoud, Siva Kumar Sastry Hari, Christopher W. Fletcher, Sarita V. Adve, Charbel Sakr, Naresh R. Shanbhag, Pavlo Molchanov, Michael B. Sullivan, Timothy Tsai, Stephen W. KecklerList of authors in order
- Landing page
-
https://arxiv.org/abs/2002.09786Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2002.09786Direct 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/2002.09786Direct OA link when available
- Concepts
-
Computer science, Heuristics, Convolutional neural network, Vulnerability (computing), Overhead (engineering), Computation, Resilience (materials science), Inference, Feature (linguistics), Software, Computer engineering, Artificial intelligence, Machine learning, Real-time computing, Data mining, Pattern recognition (psychology), Algorithm, Computer security, Linguistics, Programming language, Thermodynamics, Philosophy, Operating system, PhysicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
12Total citation count in OpenAlex
- Citations by year (recent)
-
2023: 2, 2022: 1, 2021: 9Per-year citation counts (last 5 years)
- References (count)
-
26Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3008300587 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2002.09786 |
| ids.doi | https://doi.org/10.48550/arxiv.2002.09786 |
| ids.mag | 3008300587 |
| ids.openalex | https://openalex.org/W3008300587 |
| fwci | |
| type | preprint |
| title | HarDNN: Feature Map Vulnerability Evaluation in CNNs |
| 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 | 0.9991000294685364 |
| 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/T11005 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9941999912261963 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2208 |
| topics[1].subfield.display_name | Electrical and Electronic Engineering |
| topics[1].display_name | Radiation Effects in Electronics |
| topics[2].id | https://openalex.org/T14117 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9702000021934509 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2208 |
| topics[2].subfield.display_name | Electrical and Electronic Engineering |
| topics[2].display_name | Integrated Circuits and Semiconductor Failure Analysis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7627341747283936 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C127705205 |
| concepts[1].level | 2 |
| concepts[1].score | 0.743360698223114 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q5748245 |
| concepts[1].display_name | Heuristics |
| concepts[2].id | https://openalex.org/C81363708 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7017186880111694 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[2].display_name | Convolutional neural network |
| concepts[3].id | https://openalex.org/C95713431 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6647486090660095 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q631425 |
| concepts[3].display_name | Vulnerability (computing) |
| concepts[4].id | https://openalex.org/C2779960059 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6492405533790588 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q7113681 |
| concepts[4].display_name | Overhead (engineering) |
| concepts[5].id | https://openalex.org/C45374587 |
| concepts[5].level | 2 |
| concepts[5].score | 0.6354162096977234 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q12525525 |
| concepts[5].display_name | Computation |
| concepts[6].id | https://openalex.org/C2779585090 |
| concepts[6].level | 2 |
| concepts[6].score | 0.6097974181175232 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q3457762 |
| concepts[6].display_name | Resilience (materials science) |
| concepts[7].id | https://openalex.org/C2776214188 |
| concepts[7].level | 2 |
| concepts[7].score | 0.559246301651001 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[7].display_name | Inference |
| concepts[8].id | https://openalex.org/C2776401178 |
| concepts[8].level | 2 |
| concepts[8].score | 0.5487573146820068 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[8].display_name | Feature (linguistics) |
| concepts[9].id | https://openalex.org/C2777904410 |
| concepts[9].level | 2 |
| concepts[9].score | 0.5430310964584351 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7397 |
| concepts[9].display_name | Software |
| concepts[10].id | https://openalex.org/C113775141 |
| concepts[10].level | 1 |
| concepts[10].score | 0.4485515356063843 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q428691 |
| concepts[10].display_name | Computer engineering |
| concepts[11].id | https://openalex.org/C154945302 |
| concepts[11].level | 1 |
| concepts[11].score | 0.3837434649467468 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[11].display_name | Artificial intelligence |
| concepts[12].id | https://openalex.org/C119857082 |
| concepts[12].level | 1 |
| concepts[12].score | 0.37868884205818176 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[12].display_name | Machine learning |
| concepts[13].id | https://openalex.org/C79403827 |
| concepts[13].level | 1 |
| concepts[13].score | 0.34628695249557495 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q3988 |
| concepts[13].display_name | Real-time computing |
| concepts[14].id | https://openalex.org/C124101348 |
| concepts[14].level | 1 |
| concepts[14].score | 0.32675230503082275 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q172491 |
| concepts[14].display_name | Data mining |
| concepts[15].id | https://openalex.org/C153180895 |
| concepts[15].level | 2 |
| concepts[15].score | 0.3217904269695282 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[15].display_name | Pattern recognition (psychology) |
| concepts[16].id | https://openalex.org/C11413529 |
| concepts[16].level | 1 |
| concepts[16].score | 0.27837979793548584 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[16].display_name | Algorithm |
| concepts[17].id | https://openalex.org/C38652104 |
| concepts[17].level | 1 |
| concepts[17].score | 0.20433878898620605 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[17].display_name | Computer security |
| concepts[18].id | https://openalex.org/C41895202 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[18].display_name | Linguistics |
| concepts[19].id | https://openalex.org/C199360897 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[19].display_name | Programming language |
| concepts[20].id | https://openalex.org/C97355855 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q11473 |
| concepts[20].display_name | Thermodynamics |
| concepts[21].id | https://openalex.org/C138885662 |
| concepts[21].level | 0 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[21].display_name | Philosophy |
| concepts[22].id | https://openalex.org/C111919701 |
| concepts[22].level | 1 |
| concepts[22].score | 0.0 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[22].display_name | Operating system |
| concepts[23].id | https://openalex.org/C121332964 |
| concepts[23].level | 0 |
| concepts[23].score | 0.0 |
| concepts[23].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[23].display_name | Physics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7627341747283936 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/heuristics |
| keywords[1].score | 0.743360698223114 |
| keywords[1].display_name | Heuristics |
| keywords[2].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[2].score | 0.7017186880111694 |
| keywords[2].display_name | Convolutional neural network |
| keywords[3].id | https://openalex.org/keywords/vulnerability |
| keywords[3].score | 0.6647486090660095 |
| keywords[3].display_name | Vulnerability (computing) |
| keywords[4].id | https://openalex.org/keywords/overhead |
| keywords[4].score | 0.6492405533790588 |
| keywords[4].display_name | Overhead (engineering) |
| keywords[5].id | https://openalex.org/keywords/computation |
| keywords[5].score | 0.6354162096977234 |
| keywords[5].display_name | Computation |
| keywords[6].id | https://openalex.org/keywords/resilience |
| keywords[6].score | 0.6097974181175232 |
| keywords[6].display_name | Resilience (materials science) |
| keywords[7].id | https://openalex.org/keywords/inference |
| keywords[7].score | 0.559246301651001 |
| keywords[7].display_name | Inference |
| keywords[8].id | https://openalex.org/keywords/feature |
| keywords[8].score | 0.5487573146820068 |
| keywords[8].display_name | Feature (linguistics) |
| keywords[9].id | https://openalex.org/keywords/software |
| keywords[9].score | 0.5430310964584351 |
| keywords[9].display_name | Software |
| keywords[10].id | https://openalex.org/keywords/computer-engineering |
| keywords[10].score | 0.4485515356063843 |
| keywords[10].display_name | Computer engineering |
| keywords[11].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[11].score | 0.3837434649467468 |
| keywords[11].display_name | Artificial intelligence |
| keywords[12].id | https://openalex.org/keywords/machine-learning |
| keywords[12].score | 0.37868884205818176 |
| keywords[12].display_name | Machine learning |
| keywords[13].id | https://openalex.org/keywords/real-time-computing |
| keywords[13].score | 0.34628695249557495 |
| keywords[13].display_name | Real-time computing |
| keywords[14].id | https://openalex.org/keywords/data-mining |
| keywords[14].score | 0.32675230503082275 |
| keywords[14].display_name | Data mining |
| keywords[15].id | https://openalex.org/keywords/pattern-recognition |
| keywords[15].score | 0.3217904269695282 |
| keywords[15].display_name | Pattern recognition (psychology) |
| keywords[16].id | https://openalex.org/keywords/algorithm |
| keywords[16].score | 0.27837979793548584 |
| keywords[16].display_name | Algorithm |
| keywords[17].id | https://openalex.org/keywords/computer-security |
| keywords[17].score | 0.20433878898620605 |
| keywords[17].display_name | Computer security |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2002.09786 |
| 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/2002.09786 |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2002.09786 |
| locations[1].id | mag:3008300587 |
| 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/2002.09786 |
| locations[2].id | doi:10.48550/arxiv.2002.09786 |
| 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 | |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | article |
| locations[2].license_id | |
| 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.2002.09786 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5069728263 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Abdulrahman Mahmoud |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I157725225 |
| authorships[0].affiliations[0].raw_affiliation_string | ***University of Illinois at Urbana-Champaign |
| authorships[0].institutions[0].id | https://openalex.org/I157725225 |
| authorships[0].institutions[0].ror | https://ror.org/047426m28 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I157725225 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | University of Illinois Urbana-Champaign |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Abdulrahman Mahmoud |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | ***University of Illinois at Urbana-Champaign |
| authorships[1].author.id | https://openalex.org/A5054590774 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8346-7981 |
| authorships[1].author.display_name | Siva Kumar Sastry Hari |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Siva Kumar Sastry Hari |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5027987862 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-9995-5995 |
| authorships[2].author.display_name | Christopher W. Fletcher |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Christopher W. Fletcher |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5086111967 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3403-5119 |
| authorships[3].author.display_name | Sarita V. Adve |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Sarita V. Adve |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5047303294 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-5641-0541 |
| authorships[4].author.display_name | Charbel Sakr |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Charbel Sakr |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5057014407 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-4323-9164 |
| authorships[5].author.display_name | Naresh R. Shanbhag |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Naresh R. Shanbhag |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5066945976 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Pavlo Molchanov |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Pavlo Molchanov |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5076752182 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-6537-2065 |
| authorships[7].author.display_name | Michael B. Sullivan |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Michael B. Sullivan |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5027550136 |
| authorships[8].author.orcid | https://orcid.org/0000-0001-8190-675X |
| authorships[8].author.display_name | Timothy Tsai |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Timothy Tsai |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5063354509 |
| authorships[9].author.orcid | https://orcid.org/0000-0001-6701-6099 |
| authorships[9].author.display_name | Stephen W. Keckler |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Stephen W. Keckler |
| authorships[9].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2002.09786 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | HarDNN: Feature Map Vulnerability Evaluation in CNNs |
| 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 | 0.9991000294685364 |
| 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/W3014034225, https://openalex.org/W2767260595, https://openalex.org/W3000371584, https://openalex.org/W2886321931, https://openalex.org/W3194300811, https://openalex.org/W2990630017, https://openalex.org/W3092531706, https://openalex.org/W2774688396, https://openalex.org/W3035117916, https://openalex.org/W3016678144, https://openalex.org/W2770707420, https://openalex.org/W2940764740, https://openalex.org/W3090586977, https://openalex.org/W2524222289, https://openalex.org/W2736585828, https://openalex.org/W2957419742, https://openalex.org/W3016243202, https://openalex.org/W3041816437, https://openalex.org/W3174943183, https://openalex.org/W3186714066 |
| cited_by_count | 12 |
| counts_by_year[0].year | 2023 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2022 |
| counts_by_year[1].cited_by_count | 1 |
| counts_by_year[2].year | 2021 |
| counts_by_year[2].cited_by_count | 9 |
| locations_count | 3 |
| best_oa_location.id | pmh:oai:arXiv.org:2002.09786 |
| 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/2002.09786 |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2002.09786 |
| primary_location.id | pmh:oai:arXiv.org:2002.09786 |
| 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/2002.09786 |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2002.09786 |
| publication_date | 2020-02-22 |
| publication_year | 2020 |
| referenced_works | https://openalex.org/W2899771611, https://openalex.org/W2890770683, https://openalex.org/W2741318576, https://openalex.org/W2890311316, https://openalex.org/W2561860907, https://openalex.org/W2884336760, https://openalex.org/W2983012040, https://openalex.org/W2292932312, https://openalex.org/W2735162286, https://openalex.org/W2117539524, https://openalex.org/W2101473122, https://openalex.org/W2150267144, https://openalex.org/W1619770058, https://openalex.org/W2798273231, https://openalex.org/W2626574314, https://openalex.org/W2123907700, https://openalex.org/W2132362854, https://openalex.org/W2529578574, https://openalex.org/W2962965870, https://openalex.org/W2767260595, https://openalex.org/W2528344430, https://openalex.org/W2157762234, https://openalex.org/W2883034956, https://openalex.org/W2140433506, https://openalex.org/W2247093607, https://openalex.org/W2926761828 |
| referenced_works_count | 26 |
| abstract_inverted_index.a | 49, 57, 77, 90, 97 |
| abstract_inverted_index.As | 0 |
| abstract_inverted_index.We | 80 |
| abstract_inverted_index.by | 154 |
| abstract_inverted_index.in | 9, 19, 35, 73, 94, 138 |
| abstract_inverted_index.is | 13, 144 |
| abstract_inverted_index.it | 12 |
| abstract_inverted_index.of | 22, 76, 89 |
| abstract_inverted_index.on | 65, 110 |
| abstract_inverted_index.to | 52, 129 |
| abstract_inverted_index.we | 113 |
| abstract_inverted_index.10x | 155 |
| abstract_inverted_index.30% | 158 |
| abstract_inverted_index.CNN | 58 |
| abstract_inverted_index.For | 148 |
| abstract_inverted_index.and | 60, 102, 120 |
| abstract_inverted_index.are | 5 |
| abstract_inverted_index.can | 39, 84, 127 |
| abstract_inverted_index.for | 105, 140 |
| abstract_inverted_index.map | 92 |
| abstract_inverted_index.may | 28 |
| abstract_inverted_index.the | 20, 70, 74, 115, 124, 136, 141 |
| abstract_inverted_index.use | 128 |
| abstract_inverted_index.CNNs | 95 |
| abstract_inverted_index.This | 45 |
| abstract_inverted_index.face | 21 |
| abstract_inverted_index.fast | 106 |
| abstract_inverted_index.just | 157 |
| abstract_inverted_index.show | 81, 134 |
| abstract_inverted_index.that | 15, 82, 123, 135 |
| abstract_inverted_index.them | 63 |
| abstract_inverted_index.they | 16 |
| abstract_inverted_index.with | 146, 156 |
| abstract_inverted_index.Based | 109 |
| abstract_inverted_index.added | 142 |
| abstract_inverted_index.based | 64 |
| abstract_inverted_index.being | 7 |
| abstract_inverted_index.error | 99, 118 |
| abstract_inverted_index.paper | 46 |
| abstract_inverted_index.state | 31 |
| abstract_inverted_index.their | 66 |
| abstract_inverted_index.these | 111 |
| abstract_inverted_index.using | 96 |
| abstract_inverted_index.which | 38 |
| abstract_inverted_index.(CNNs) | 4 |
| abstract_inverted_index.(fmap) | 93 |
| abstract_inverted_index.HarDNN | 83, 150 |
| abstract_inverted_index.Neural | 2 |
| abstract_inverted_index.affect | 41 |
| abstract_inverted_index.behave | 17 |
| abstract_inverted_index.during | 32, 56 |
| abstract_inverted_index.employ | 130 |
| abstract_inverted_index.error. | 79 |
| abstract_inverted_index.errors | 27, 37 |
| abstract_inverted_index.output | 72 |
| abstract_inverted_index.system | 125 |
| abstract_inverted_index.HarDNN, | 48 |
| abstract_inverted_index.HarDNN. | 147 |
| abstract_inverted_index.Results | 133 |
| abstract_inverted_index.analyze | 114 |
| abstract_inverted_index.between | 117 |
| abstract_inverted_index.errors. | 24 |
| abstract_inverted_index.explore | 103 |
| abstract_inverted_index.feature | 91 |
| abstract_inverted_index.making. | 44 |
| abstract_inverted_index.protect | 62 |
| abstract_inverted_index.towards | 68 |
| abstract_inverted_index.Networks | 3 |
| abstract_inverted_index.approach | 51 |
| abstract_inverted_index.coverage | 119 |
| abstract_inverted_index.decision | 43 |
| abstract_inverted_index.employed | 8 |
| abstract_inverted_index.estimate | 86 |
| abstract_inverted_index.example, | 149 |
| abstract_inverted_index.hardware | 23, 26, 78 |
| abstract_inverted_index.identify | 53 |
| abstract_inverted_index.improves | 151 |
| abstract_inverted_index.overhead | 122 |
| abstract_inverted_index.presence | 75 |
| abstract_inverted_index.presents | 47 |
| abstract_inverted_index.relative | 87 |
| abstract_inverted_index.reliably | 18 |
| abstract_inverted_index.results, | 112 |
| abstract_inverted_index.tradeoff | 116 |
| abstract_inverted_index.Transient | 25 |
| abstract_inverted_index.adversely | 40 |
| abstract_inverted_index.campaign, | 101 |
| abstract_inverted_index.designers | 126 |
| abstract_inverted_index.important | 14 |
| abstract_inverted_index.inference | 59, 71 |
| abstract_inverted_index.injection | 100 |
| abstract_inverted_index.percolate | 29 |
| abstract_inverted_index.resulting | 34 |
| abstract_inverted_index.selective | 131 |
| abstract_inverted_index.accurately | 85 |
| abstract_inverted_index.additional | 159 |
| abstract_inverted_index.corrupting | 69 |
| abstract_inverted_index.execution, | 33 |
| abstract_inverted_index.heuristics | 104 |
| abstract_inverted_index.high-level | 42 |
| abstract_inverted_index.propensity | 67 |
| abstract_inverted_index.resilience | 139, 153 |
| abstract_inverted_index.vulnerable | 54 |
| abstract_inverted_index.assessment. | 108 |
| abstract_inverted_index.computation | 143 |
| abstract_inverted_index.improvement | 137 |
| abstract_inverted_index.protection. | 132 |
| abstract_inverted_index.selectively | 61 |
| abstract_inverted_index.statistical | 98 |
| abstract_inverted_index.superlinear | 145 |
| abstract_inverted_index.undesirable | 30 |
| abstract_inverted_index.SqueezeNet's | 152 |
| abstract_inverted_index.computations | 55 |
| abstract_inverted_index.increasingly | 6 |
| abstract_inverted_index.Convolutional | 1 |
| abstract_inverted_index.applications, | 11 |
| abstract_inverted_index.computational | 121 |
| abstract_inverted_index.computations. | 160 |
| abstract_inverted_index.vulnerability | 88, 107 |
| abstract_inverted_index.safety-critical | 10 |
| abstract_inverted_index.software-directed | 50 |
| abstract_inverted_index.software-manifested | 36 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 10 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.7400000095367432 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile |