Towards Sustainable SecureML: Quantifying Carbon Footprint of Adversarial Machine Learning Article Swipe
Syed Mhamudul Hasan
,
Abdur R. Shahid
,
Ahmed Imteaj
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.19009
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.19009
The widespread adoption of machine learning (ML) across various industries has raised sustainability concerns due to its substantial energy usage and carbon emissions. This issue becomes more pressing in adversarial ML, which focuses on enhancing model security against different network-based attacks. Implementing defenses in ML systems often necessitates additional computational resources and network security measures, exacerbating their environmental impacts. In this paper, we pioneer the first investigation into adversarial ML's carbon footprint, providing empirical evidence connecting greater model robustness to higher emissions. Addressing the critical need to quantify this trade-off, we introduce the Robustness Carbon Trade-off Index (RCTI). This novel metric, inspired by economic elasticity principles, captures the sensitivity of carbon emissions to changes in adversarial robustness. We demonstrate the RCTI through an experiment involving evasion attacks, analyzing the interplay between robustness against attacks, performance, and carbon emissions.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2403.19009
- https://arxiv.org/pdf/2403.19009
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4393335347
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4393335347Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2403.19009Digital Object Identifier
- Title
-
Towards Sustainable SecureML: Quantifying Carbon Footprint of Adversarial Machine LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-03-27Full publication date if available
- Authors
-
Syed Mhamudul Hasan, Abdur R. Shahid, Ahmed ImteajList of authors in order
- Landing page
-
https://arxiv.org/abs/2403.19009Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2403.19009Direct 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/2403.19009Direct OA link when available
- Concepts
-
Carbon footprint, Adversarial system, Footprint, Computer science, Artificial intelligence, Machine learning, Geography, Geology, Greenhouse gas, Archaeology, OceanographyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4393335347 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2403.19009 |
| ids.doi | https://doi.org/10.48550/arxiv.2403.19009 |
| ids.openalex | https://openalex.org/W4393335347 |
| fwci | |
| type | preprint |
| title | Towards Sustainable SecureML: Quantifying Carbon Footprint of Adversarial Machine Learning |
| 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 | 0.9866999983787537 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Adversarial Robustness in Machine Learning |
| topics[1].id | https://openalex.org/T11512 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9498999714851379 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Anomaly Detection Techniques and Applications |
| topics[2].id | https://openalex.org/T10917 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9133999943733215 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2207 |
| topics[2].subfield.display_name | Control and Systems Engineering |
| topics[2].display_name | Smart Grid Security and Resilience |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780936489 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8673725724220276 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q310667 |
| concepts[0].display_name | Carbon footprint |
| concepts[1].id | https://openalex.org/C37736160 |
| concepts[1].level | 2 |
| concepts[1].score | 0.8348917365074158 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[1].display_name | Adversarial system |
| concepts[2].id | https://openalex.org/C132943942 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7298754453659058 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q2562511 |
| concepts[2].display_name | Footprint |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5102229118347168 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4679861068725586 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.4127287268638611 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C205649164 |
| concepts[6].level | 0 |
| concepts[6].score | 0.1712956428527832 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[6].display_name | Geography |
| concepts[7].id | https://openalex.org/C127313418 |
| concepts[7].level | 0 |
| concepts[7].score | 0.12919634580612183 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1069 |
| concepts[7].display_name | Geology |
| concepts[8].id | https://openalex.org/C47737302 |
| concepts[8].level | 2 |
| concepts[8].score | 0.11572888493537903 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q167336 |
| concepts[8].display_name | Greenhouse gas |
| concepts[9].id | https://openalex.org/C166957645 |
| concepts[9].level | 1 |
| concepts[9].score | 0.06896016001701355 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q23498 |
| concepts[9].display_name | Archaeology |
| concepts[10].id | https://openalex.org/C111368507 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q43518 |
| concepts[10].display_name | Oceanography |
| keywords[0].id | https://openalex.org/keywords/carbon-footprint |
| keywords[0].score | 0.8673725724220276 |
| keywords[0].display_name | Carbon footprint |
| keywords[1].id | https://openalex.org/keywords/adversarial-system |
| keywords[1].score | 0.8348917365074158 |
| keywords[1].display_name | Adversarial system |
| keywords[2].id | https://openalex.org/keywords/footprint |
| keywords[2].score | 0.7298754453659058 |
| keywords[2].display_name | Footprint |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5102229118347168 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.4679861068725586 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.4127287268638611 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/geography |
| keywords[6].score | 0.1712956428527832 |
| keywords[6].display_name | Geography |
| keywords[7].id | https://openalex.org/keywords/geology |
| keywords[7].score | 0.12919634580612183 |
| keywords[7].display_name | Geology |
| keywords[8].id | https://openalex.org/keywords/greenhouse-gas |
| keywords[8].score | 0.11572888493537903 |
| keywords[8].display_name | Greenhouse gas |
| keywords[9].id | https://openalex.org/keywords/archaeology |
| keywords[9].score | 0.06896016001701355 |
| keywords[9].display_name | Archaeology |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2403.19009 |
| 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 | cc-by |
| locations[0].pdf_url | https://arxiv.org/pdf/2403.19009 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2403.19009 |
| locations[1].id | doi:10.48550/arxiv.2403.19009 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2403.19009 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5104326736 |
| authorships[0].author.orcid | https://orcid.org/0009-0008-7414-9103 |
| authorships[0].author.display_name | Syed Mhamudul Hasan |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Hasan, Syed Mhamudul |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5035192689 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3168-8907 |
| authorships[1].author.display_name | Abdur R. Shahid |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Shahid, Abdur R. |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5077711449 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6975-3997 |
| authorships[2].author.display_name | Ahmed Imteaj |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Imteaj, Ahmed |
| authorships[2].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2403.19009 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-03-30T00:00:00 |
| display_name | Towards Sustainable SecureML: Quantifying Carbon Footprint of Adversarial Machine Learning |
| 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 | 0.9866999983787537 |
| 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/W3104369155, https://openalex.org/W2961085424, https://openalex.org/W2162390224, https://openalex.org/W4389988448, https://openalex.org/W4320030328, https://openalex.org/W4306674287, https://openalex.org/W2031734160, https://openalex.org/W2238629651, https://openalex.org/W4366179056, https://openalex.org/W2883844485 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2403.19009 |
| 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 | cc-by |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2403.19009 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| 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/2403.19009 |
| primary_location.id | pmh:oai:arXiv.org:2403.19009 |
| 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 | cc-by |
| primary_location.pdf_url | https://arxiv.org/pdf/2403.19009 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2403.19009 |
| publication_date | 2024-03-27 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.In | 59 |
| abstract_inverted_index.ML | 44 |
| abstract_inverted_index.We | 117 |
| abstract_inverted_index.an | 122 |
| abstract_inverted_index.by | 102 |
| abstract_inverted_index.in | 28, 43, 114 |
| abstract_inverted_index.of | 3, 109 |
| abstract_inverted_index.on | 33 |
| abstract_inverted_index.to | 15, 79, 86, 112 |
| abstract_inverted_index.we | 62, 90 |
| abstract_inverted_index.ML, | 30 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 20, 51, 135 |
| abstract_inverted_index.due | 14 |
| abstract_inverted_index.has | 10 |
| abstract_inverted_index.its | 16 |
| abstract_inverted_index.the | 64, 83, 92, 107, 119, 128 |
| abstract_inverted_index.(ML) | 6 |
| abstract_inverted_index.ML's | 69 |
| abstract_inverted_index.RCTI | 120 |
| abstract_inverted_index.This | 23, 98 |
| abstract_inverted_index.into | 67 |
| abstract_inverted_index.more | 26 |
| abstract_inverted_index.need | 85 |
| abstract_inverted_index.this | 60, 88 |
| abstract_inverted_index.Index | 96 |
| abstract_inverted_index.first | 65 |
| abstract_inverted_index.issue | 24 |
| abstract_inverted_index.model | 35, 77 |
| abstract_inverted_index.novel | 99 |
| abstract_inverted_index.often | 46 |
| abstract_inverted_index.their | 56 |
| abstract_inverted_index.usage | 19 |
| abstract_inverted_index.which | 31 |
| abstract_inverted_index.Carbon | 94 |
| abstract_inverted_index.across | 7 |
| abstract_inverted_index.carbon | 21, 70, 110, 136 |
| abstract_inverted_index.energy | 18 |
| abstract_inverted_index.higher | 80 |
| abstract_inverted_index.paper, | 61 |
| abstract_inverted_index.raised | 11 |
| abstract_inverted_index.(RCTI). | 97 |
| abstract_inverted_index.against | 37, 132 |
| abstract_inverted_index.becomes | 25 |
| abstract_inverted_index.between | 130 |
| abstract_inverted_index.changes | 113 |
| abstract_inverted_index.evasion | 125 |
| abstract_inverted_index.focuses | 32 |
| abstract_inverted_index.greater | 76 |
| abstract_inverted_index.machine | 4 |
| abstract_inverted_index.metric, | 100 |
| abstract_inverted_index.network | 52 |
| abstract_inverted_index.pioneer | 63 |
| abstract_inverted_index.systems | 45 |
| abstract_inverted_index.through | 121 |
| abstract_inverted_index.various | 8 |
| abstract_inverted_index.adoption | 2 |
| abstract_inverted_index.attacks, | 126, 133 |
| abstract_inverted_index.attacks. | 40 |
| abstract_inverted_index.captures | 106 |
| abstract_inverted_index.concerns | 13 |
| abstract_inverted_index.critical | 84 |
| abstract_inverted_index.defenses | 42 |
| abstract_inverted_index.economic | 103 |
| abstract_inverted_index.evidence | 74 |
| abstract_inverted_index.impacts. | 58 |
| abstract_inverted_index.inspired | 101 |
| abstract_inverted_index.learning | 5 |
| abstract_inverted_index.pressing | 27 |
| abstract_inverted_index.quantify | 87 |
| abstract_inverted_index.security | 36, 53 |
| abstract_inverted_index.Trade-off | 95 |
| abstract_inverted_index.analyzing | 127 |
| abstract_inverted_index.different | 38 |
| abstract_inverted_index.emissions | 111 |
| abstract_inverted_index.empirical | 73 |
| abstract_inverted_index.enhancing | 34 |
| abstract_inverted_index.interplay | 129 |
| abstract_inverted_index.introduce | 91 |
| abstract_inverted_index.involving | 124 |
| abstract_inverted_index.measures, | 54 |
| abstract_inverted_index.providing | 72 |
| abstract_inverted_index.resources | 50 |
| abstract_inverted_index.Addressing | 82 |
| abstract_inverted_index.Robustness | 93 |
| abstract_inverted_index.additional | 48 |
| abstract_inverted_index.connecting | 75 |
| abstract_inverted_index.elasticity | 104 |
| abstract_inverted_index.emissions. | 22, 81, 137 |
| abstract_inverted_index.experiment | 123 |
| abstract_inverted_index.footprint, | 71 |
| abstract_inverted_index.industries | 9 |
| abstract_inverted_index.robustness | 78, 131 |
| abstract_inverted_index.trade-off, | 89 |
| abstract_inverted_index.widespread | 1 |
| abstract_inverted_index.adversarial | 29, 68, 115 |
| abstract_inverted_index.demonstrate | 118 |
| abstract_inverted_index.principles, | 105 |
| abstract_inverted_index.robustness. | 116 |
| abstract_inverted_index.sensitivity | 108 |
| abstract_inverted_index.substantial | 17 |
| abstract_inverted_index.Implementing | 41 |
| abstract_inverted_index.exacerbating | 55 |
| abstract_inverted_index.necessitates | 47 |
| abstract_inverted_index.performance, | 134 |
| abstract_inverted_index.computational | 49 |
| abstract_inverted_index.environmental | 57 |
| abstract_inverted_index.investigation | 66 |
| abstract_inverted_index.network-based | 39 |
| abstract_inverted_index.sustainability | 12 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |