MILR: Mathematically Induced Layer Recovery for Plaintext Space Error Correction of CNNs Article Swipe
Jonathan Ponader
,
Sandip Kundu
,
Yan Solihin
·
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2010.14687
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2010.14687
The increased use of Convolutional Neural Networks (CNN) in mission critical systems has increased the need for robust and resilient networks in the face of both naturally occurring faults as well as security attacks. The lack of robustness and resiliency can lead to unreliable inference results. Current methods that address CNN robustness require hardware modification, network modification, or network duplication. This paper proposes MILR a software based CNN error detection and error correction system that enables self-healing of the network from single and multi bit errors. The self-healing capabilities are based on mathematical relationships between the inputs,outputs, and parameters(weights) of a layers, exploiting these relationships allow the recovery of erroneous parameters (weights) throughout a layer and the network. MILR is suitable for plaintext-space error correction (PSEC) given its ability to correct whole-weight and even whole-layer errors in CNNs.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2010.14687
- https://arxiv.org/pdf/2010.14687
- OA Status
- green
- Cited By
- 1
- References
- 18
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3095146057
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3095146057Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2010.14687Digital Object Identifier
- Title
-
MILR: Mathematically Induced Layer Recovery for Plaintext Space Error Correction of CNNsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2020Year of publication
- Publication date
-
2020-10-28Full publication date if available
- Authors
-
Jonathan Ponader, Sandip Kundu, Yan SolihinList of authors in order
- Landing page
-
https://arxiv.org/abs/2010.14687Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2010.14687Direct 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/2010.14687Direct OA link when available
- Concepts
-
Computer science, Robustness (evolution), Convolutional neural network, Error detection and correction, Plaintext, Inference, Algorithm, Theoretical computer science, Computer engineering, Artificial intelligence, Encryption, Computer network, Chemistry, Gene, BiochemistryTop 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)
-
18Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3095146057 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2010.14687 |
| ids.doi | https://doi.org/10.48550/arxiv.2010.14687 |
| ids.mag | 3095146057 |
| ids.openalex | https://openalex.org/W3095146057 |
| fwci | |
| type | preprint |
| title | MILR: Mathematically Induced Layer Recovery for Plaintext Space Error Correction of 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 | 0.9994999766349792 |
| 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/T14117 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9988999962806702 |
| 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 | Integrated Circuits and Semiconductor Failure Analysis |
| topics[2].id | https://openalex.org/T12122 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9968000054359436 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1708 |
| topics[2].subfield.display_name | Hardware and Architecture |
| topics[2].display_name | Physical Unclonable Functions (PUFs) and Hardware Security |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7716684341430664 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C63479239 |
| concepts[1].level | 3 |
| concepts[1].score | 0.7653959393501282 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[1].display_name | Robustness (evolution) |
| concepts[2].id | https://openalex.org/C81363708 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5680578351020813 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[2].display_name | Convolutional neural network |
| concepts[3].id | https://openalex.org/C103088060 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5500963926315308 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1062839 |
| concepts[3].display_name | Error detection and correction |
| concepts[4].id | https://openalex.org/C92717368 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5352702140808105 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1162538 |
| concepts[4].display_name | Plaintext |
| concepts[5].id | https://openalex.org/C2776214188 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5085099935531616 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[5].display_name | Inference |
| concepts[6].id | https://openalex.org/C11413529 |
| concepts[6].level | 1 |
| concepts[6].score | 0.48684805631637573 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[6].display_name | Algorithm |
| concepts[7].id | https://openalex.org/C80444323 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3463655412197113 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[7].display_name | Theoretical computer science |
| concepts[8].id | https://openalex.org/C113775141 |
| concepts[8].level | 1 |
| concepts[8].score | 0.33673393726348877 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q428691 |
| concepts[8].display_name | Computer engineering |
| concepts[9].id | https://openalex.org/C154945302 |
| concepts[9].level | 1 |
| concepts[9].score | 0.2532846927642822 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[9].display_name | Artificial intelligence |
| concepts[10].id | https://openalex.org/C148730421 |
| concepts[10].level | 2 |
| concepts[10].score | 0.18664690852165222 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q141090 |
| concepts[10].display_name | Encryption |
| concepts[11].id | https://openalex.org/C31258907 |
| concepts[11].level | 1 |
| concepts[11].score | 0.13899630308151245 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[11].display_name | Computer network |
| concepts[12].id | https://openalex.org/C185592680 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[12].display_name | Chemistry |
| concepts[13].id | https://openalex.org/C104317684 |
| concepts[13].level | 2 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[13].display_name | Gene |
| concepts[14].id | https://openalex.org/C55493867 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[14].display_name | Biochemistry |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7716684341430664 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/robustness |
| keywords[1].score | 0.7653959393501282 |
| keywords[1].display_name | Robustness (evolution) |
| keywords[2].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[2].score | 0.5680578351020813 |
| keywords[2].display_name | Convolutional neural network |
| keywords[3].id | https://openalex.org/keywords/error-detection-and-correction |
| keywords[3].score | 0.5500963926315308 |
| keywords[3].display_name | Error detection and correction |
| keywords[4].id | https://openalex.org/keywords/plaintext |
| keywords[4].score | 0.5352702140808105 |
| keywords[4].display_name | Plaintext |
| keywords[5].id | https://openalex.org/keywords/inference |
| keywords[5].score | 0.5085099935531616 |
| keywords[5].display_name | Inference |
| keywords[6].id | https://openalex.org/keywords/algorithm |
| keywords[6].score | 0.48684805631637573 |
| keywords[6].display_name | Algorithm |
| keywords[7].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[7].score | 0.3463655412197113 |
| keywords[7].display_name | Theoretical computer science |
| keywords[8].id | https://openalex.org/keywords/computer-engineering |
| keywords[8].score | 0.33673393726348877 |
| keywords[8].display_name | Computer engineering |
| keywords[9].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[9].score | 0.2532846927642822 |
| keywords[9].display_name | Artificial intelligence |
| keywords[10].id | https://openalex.org/keywords/encryption |
| keywords[10].score | 0.18664690852165222 |
| keywords[10].display_name | Encryption |
| keywords[11].id | https://openalex.org/keywords/computer-network |
| keywords[11].score | 0.13899630308151245 |
| keywords[11].display_name | Computer network |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2010.14687 |
| 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/2010.14687 |
| 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/2010.14687 |
| locations[1].id | doi:10.48550/arxiv.2010.14687 |
| 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 | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2010.14687 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5070240495 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Jonathan Ponader |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Jonathan Ponader |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5054064879 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8221-3824 |
| authorships[1].author.display_name | Sandip Kundu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Sandip Kundu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5061775189 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-8863-941X |
| authorships[2].author.display_name | Yan Solihin |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Yan Solihin |
| authorships[2].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2010.14687 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | MILR: Mathematically Induced Layer Recovery for Plaintext Space Error Correction of CNNs |
| has_fulltext | True |
| 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 | 0.9994999766349792 |
| 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/W4293226380, https://openalex.org/W2055243143, https://openalex.org/W4321487865, https://openalex.org/W4313906399, https://openalex.org/W4391266461, https://openalex.org/W2590798552, https://openalex.org/W2811106690, https://openalex.org/W2394408226, https://openalex.org/W4389168214, https://openalex.org/W4366457933 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2021 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2010.14687 |
| 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/2010.14687 |
| 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/2010.14687 |
| primary_location.id | pmh:oai:arXiv.org:2010.14687 |
| 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/2010.14687 |
| 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/2010.14687 |
| publication_date | 2020-10-28 |
| publication_year | 2020 |
| referenced_works | https://openalex.org/W2273396394, https://openalex.org/W2144784023, https://openalex.org/W3118608800, https://openalex.org/W2167677193, https://openalex.org/W2122249806, https://openalex.org/W2754815949, https://openalex.org/W2001047056, https://openalex.org/W3112402894, https://openalex.org/W2771112233, https://openalex.org/W2767260595, https://openalex.org/W2962835968, https://openalex.org/W2796384729, https://openalex.org/W2157447136, https://openalex.org/W2990993977, https://openalex.org/W1993660990, https://openalex.org/W2120185818, https://openalex.org/W2981860227, https://openalex.org/W2117539524 |
| referenced_works_count | 18 |
| abstract_inverted_index.a | 64, 100, 113 |
| abstract_inverted_index.as | 29, 31 |
| abstract_inverted_index.in | 8, 21, 136 |
| abstract_inverted_index.is | 119 |
| abstract_inverted_index.of | 3, 24, 36, 77, 99, 108 |
| abstract_inverted_index.on | 91 |
| abstract_inverted_index.or | 57 |
| abstract_inverted_index.to | 42, 129 |
| abstract_inverted_index.CNN | 50, 67 |
| abstract_inverted_index.The | 0, 34, 86 |
| abstract_inverted_index.and | 18, 38, 70, 82, 97, 115, 132 |
| abstract_inverted_index.are | 89 |
| abstract_inverted_index.bit | 84 |
| abstract_inverted_index.can | 40 |
| abstract_inverted_index.for | 16, 121 |
| abstract_inverted_index.has | 12 |
| abstract_inverted_index.its | 127 |
| abstract_inverted_index.the | 14, 22, 78, 95, 106, 116 |
| abstract_inverted_index.use | 2 |
| abstract_inverted_index.MILR | 63, 118 |
| abstract_inverted_index.This | 60 |
| abstract_inverted_index.both | 25 |
| abstract_inverted_index.even | 133 |
| abstract_inverted_index.face | 23 |
| abstract_inverted_index.from | 80 |
| abstract_inverted_index.lack | 35 |
| abstract_inverted_index.lead | 41 |
| abstract_inverted_index.need | 15 |
| abstract_inverted_index.that | 48, 74 |
| abstract_inverted_index.well | 30 |
| abstract_inverted_index.(CNN) | 7 |
| abstract_inverted_index.CNNs. | 137 |
| abstract_inverted_index.allow | 105 |
| abstract_inverted_index.based | 66, 90 |
| abstract_inverted_index.error | 68, 71, 123 |
| abstract_inverted_index.given | 126 |
| abstract_inverted_index.layer | 114 |
| abstract_inverted_index.multi | 83 |
| abstract_inverted_index.paper | 61 |
| abstract_inverted_index.these | 103 |
| abstract_inverted_index.(PSEC) | 125 |
| abstract_inverted_index.Neural | 5 |
| abstract_inverted_index.errors | 135 |
| abstract_inverted_index.faults | 28 |
| abstract_inverted_index.robust | 17 |
| abstract_inverted_index.single | 81 |
| abstract_inverted_index.system | 73 |
| abstract_inverted_index.Current | 46 |
| abstract_inverted_index.ability | 128 |
| abstract_inverted_index.address | 49 |
| abstract_inverted_index.between | 94 |
| abstract_inverted_index.correct | 130 |
| abstract_inverted_index.enables | 75 |
| abstract_inverted_index.errors. | 85 |
| abstract_inverted_index.layers, | 101 |
| abstract_inverted_index.methods | 47 |
| abstract_inverted_index.mission | 9 |
| abstract_inverted_index.network | 55, 58, 79 |
| abstract_inverted_index.require | 52 |
| abstract_inverted_index.systems | 11 |
| abstract_inverted_index.Networks | 6 |
| abstract_inverted_index.attacks. | 33 |
| abstract_inverted_index.critical | 10 |
| abstract_inverted_index.hardware | 53 |
| abstract_inverted_index.network. | 117 |
| abstract_inverted_index.networks | 20 |
| abstract_inverted_index.proposes | 62 |
| abstract_inverted_index.recovery | 107 |
| abstract_inverted_index.results. | 45 |
| abstract_inverted_index.security | 32 |
| abstract_inverted_index.software | 65 |
| abstract_inverted_index.suitable | 120 |
| abstract_inverted_index.(weights) | 111 |
| abstract_inverted_index.detection | 69 |
| abstract_inverted_index.erroneous | 109 |
| abstract_inverted_index.increased | 1, 13 |
| abstract_inverted_index.inference | 44 |
| abstract_inverted_index.naturally | 26 |
| abstract_inverted_index.occurring | 27 |
| abstract_inverted_index.resilient | 19 |
| abstract_inverted_index.correction | 72, 124 |
| abstract_inverted_index.exploiting | 102 |
| abstract_inverted_index.parameters | 110 |
| abstract_inverted_index.resiliency | 39 |
| abstract_inverted_index.robustness | 37, 51 |
| abstract_inverted_index.throughout | 112 |
| abstract_inverted_index.unreliable | 43 |
| abstract_inverted_index.whole-layer | 134 |
| abstract_inverted_index.capabilities | 88 |
| abstract_inverted_index.duplication. | 59 |
| abstract_inverted_index.mathematical | 92 |
| abstract_inverted_index.self-healing | 76, 87 |
| abstract_inverted_index.whole-weight | 131 |
| abstract_inverted_index.Convolutional | 4 |
| abstract_inverted_index.modification, | 54, 56 |
| abstract_inverted_index.relationships | 93, 104 |
| abstract_inverted_index.inputs,outputs, | 96 |
| abstract_inverted_index.plaintext-space | 122 |
| abstract_inverted_index.parameters(weights) | 98 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |