StAIn: Stealthy Avenues of Attacks on Horizontally Collaborated Convolutional Neural Network Inference and Their Mitigation Article Swipe
Adewale Adeyemo
,
Jonathan Sanderson
,
Tolulope A. Odetola
,
Faiq Khalid
,
Syed Rafay Hasan
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1109/access.2023.3241096
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1109/access.2023.3241096
With significant potential improvement in device-to-device (D2D) communication due to improved wireless link capacity (e.g., 5G and NextG systems), a collaboration of multiple edge devices (called horizontal collaboration (HC)) is becoming a reality for real-time Edge Intelligence (EI). The distributed nature of HC offers an advantage against traditional adversarial attacks because the adversary does not have access to the entire deep learning architecture (DLA). Due to the involvement of multiple untrusted edge devices in HC environment, the possibility of malicious devices cannot be eliminated. In this paper, we unearth some attacks that are very effective and stealthy even when the attacker has minimal knowledge of the DLA as is the case in HC-based DLA. We are also providing novel filtering methods to mitigate such attacks. Our novel attacks leverage local information available on output feature maps (FMs) of a targeted edge device to modify the regular adversarial attacks (e.g. Fast Gradient Signed Method (FGSM) and Jacobian-based Saliency Map Attack (JSMA)). Similarly, a customized convolutional neural network (CNN) based filter is empirically designed, developed, and tested. Four different CNN models (LeNet, CapsuleNet, MiniVGGNet, and VGG16) are used to validate the proposed attacks and defense methodologies. Our three attacks on four different CNN models (with two variations of each attack) show a substantial accuracy drop of 62% on average. The proposed filtering approach is able to mitigate the attack by recovering the actual accuracy back to 75.1% on average. To the best of our knowledge, this is the first work that investigates the security vulnerability of DLA in the HC environment, and all three of our attacks are scalable and agnostic to the partition location within the DLA.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/access.2023.3241096
- https://ieeexplore.ieee.org/ielx7/6287639/10005208/10032539.pdf
- OA Status
- gold
- Cited By
- 8
- References
- 85
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4319300189
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4319300189Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/access.2023.3241096Digital Object Identifier
- Title
-
StAIn: Stealthy Avenues of Attacks on Horizontally Collaborated Convolutional Neural Network Inference and Their MitigationWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-01-01Full publication date if available
- Authors
-
Adewale Adeyemo, Jonathan Sanderson, Tolulope A. Odetola, Faiq Khalid, Syed Rafay HasanList of authors in order
- Landing page
-
https://doi.org/10.1109/access.2023.3241096Publisher landing page
- PDF URL
-
https://ieeexplore.ieee.org/ielx7/6287639/10005208/10032539.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://ieeexplore.ieee.org/ielx7/6287639/10005208/10032539.pdfDirect OA link when available
- Concepts
-
Computer science, Leverage (statistics), Convolutional neural network, Enhanced Data Rates for GSM Evolution, Edge device, Deep learning, Artificial intelligence, Adversary, Adversarial system, Inference, Computer security, Operating system, Cloud computingTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
8Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2024: 3, 2023: 4Per-year citation counts (last 5 years)
- References (count)
-
85Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4319300189 |
|---|---|
| doi | https://doi.org/10.1109/access.2023.3241096 |
| ids.doi | https://doi.org/10.1109/access.2023.3241096 |
| ids.openalex | https://openalex.org/W4319300189 |
| fwci | 2.0435431 |
| type | article |
| title | StAIn: Stealthy Avenues of Attacks on Horizontally Collaborated Convolutional Neural Network Inference and Their Mitigation |
| awards[0].id | https://openalex.org/G2087602024 |
| awards[0].funder_id | https://openalex.org/F4320306076 |
| awards[0].display_name | |
| awards[0].funder_award_id | CNS-1852126 |
| awards[0].funder_display_name | National Science Foundation |
| biblio.issue | |
| biblio.volume | 11 |
| biblio.last_page | 10534 |
| biblio.first_page | 10520 |
| topics[0].id | https://openalex.org/T11689 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 1.0 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Adversarial Robustness in Machine Learning |
| topics[1].id | https://openalex.org/T10502 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9897000193595886 |
| 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 | Advanced Memory and Neural Computing |
| topics[2].id | https://openalex.org/T12131 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9818999767303467 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Wireless Signal Modulation Classification |
| funders[0].id | https://openalex.org/F4320306076 |
| funders[0].ror | https://ror.org/021nxhr62 |
| funders[0].display_name | National Science Foundation |
| is_xpac | False |
| apc_list.value | 1850 |
| apc_list.currency | USD |
| apc_list.value_usd | 1850 |
| apc_paid.value | 1850 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 1850 |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8130687475204468 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C153083717 |
| concepts[1].level | 2 |
| concepts[1].score | 0.750633955001831 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q6535263 |
| concepts[1].display_name | Leverage (statistics) |
| concepts[2].id | https://openalex.org/C81363708 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7306624054908752 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[2].display_name | Convolutional neural network |
| concepts[3].id | https://openalex.org/C162307627 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5932404398918152 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q204833 |
| concepts[3].display_name | Enhanced Data Rates for GSM Evolution |
| concepts[4].id | https://openalex.org/C138236772 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5486789345741272 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q25098575 |
| concepts[4].display_name | Edge device |
| concepts[5].id | https://openalex.org/C108583219 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5079248547554016 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[5].display_name | Deep learning |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.5020794868469238 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C41065033 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4707487225532532 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2825412 |
| concepts[7].display_name | Adversary |
| concepts[8].id | https://openalex.org/C37736160 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4468268156051636 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[8].display_name | Adversarial system |
| concepts[9].id | https://openalex.org/C2776214188 |
| concepts[9].level | 2 |
| concepts[9].score | 0.43613579869270325 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[9].display_name | Inference |
| concepts[10].id | https://openalex.org/C38652104 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3805714249610901 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[10].display_name | Computer security |
| concepts[11].id | https://openalex.org/C111919701 |
| concepts[11].level | 1 |
| concepts[11].score | 0.07557997107505798 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[11].display_name | Operating system |
| concepts[12].id | https://openalex.org/C79974875 |
| concepts[12].level | 2 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q483639 |
| concepts[12].display_name | Cloud computing |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8130687475204468 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/leverage |
| keywords[1].score | 0.750633955001831 |
| keywords[1].display_name | Leverage (statistics) |
| keywords[2].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[2].score | 0.7306624054908752 |
| keywords[2].display_name | Convolutional neural network |
| keywords[3].id | https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution |
| keywords[3].score | 0.5932404398918152 |
| keywords[3].display_name | Enhanced Data Rates for GSM Evolution |
| keywords[4].id | https://openalex.org/keywords/edge-device |
| keywords[4].score | 0.5486789345741272 |
| keywords[4].display_name | Edge device |
| keywords[5].id | https://openalex.org/keywords/deep-learning |
| keywords[5].score | 0.5079248547554016 |
| keywords[5].display_name | Deep learning |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.5020794868469238 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/adversary |
| keywords[7].score | 0.4707487225532532 |
| keywords[7].display_name | Adversary |
| keywords[8].id | https://openalex.org/keywords/adversarial-system |
| keywords[8].score | 0.4468268156051636 |
| keywords[8].display_name | Adversarial system |
| keywords[9].id | https://openalex.org/keywords/inference |
| keywords[9].score | 0.43613579869270325 |
| keywords[9].display_name | Inference |
| keywords[10].id | https://openalex.org/keywords/computer-security |
| keywords[10].score | 0.3805714249610901 |
| keywords[10].display_name | Computer security |
| keywords[11].id | https://openalex.org/keywords/operating-system |
| keywords[11].score | 0.07557997107505798 |
| keywords[11].display_name | Operating system |
| language | en |
| locations[0].id | doi:10.1109/access.2023.3241096 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S2485537415 |
| locations[0].source.issn | 2169-3536 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2169-3536 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | IEEE Access |
| locations[0].source.host_organization | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_name | Institute of Electrical and Electronics Engineers |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://ieeexplore.ieee.org/ielx7/6287639/10005208/10032539.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | IEEE Access |
| locations[0].landing_page_url | https://doi.org/10.1109/access.2023.3241096 |
| locations[1].id | pmh:oai:doaj.org/article:536b11fc1dbe4b218a15c75e5ac939a4 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306401280 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | DOAJ (DOAJ: Directory of Open Access Journals) |
| locations[1].source.host_organization | |
| locations[1].source.host_organization_name | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | IEEE Access, Vol 11, Pp 10520-10534 (2023) |
| locations[1].landing_page_url | https://doaj.org/article/536b11fc1dbe4b218a15c75e5ac939a4 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5029827645 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-2897-1138 |
| authorships[0].author.display_name | Adewale Adeyemo |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I63920570 |
| authorships[0].affiliations[0].raw_affiliation_string | Department of Electrical and Computer Engineering, Tennessee Technological University, Cookeville, TN, USA |
| authorships[0].institutions[0].id | https://openalex.org/I63920570 |
| authorships[0].institutions[0].ror | https://ror.org/05drmrq39 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I63920570 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | Tennessee Technological University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Adewale A. Adeyemo |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Department of Electrical and Computer Engineering, Tennessee Technological University, Cookeville, TN, USA |
| authorships[1].author.id | https://openalex.org/A5022649237 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-1769-8647 |
| authorships[1].author.display_name | Jonathan Sanderson |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I63920570 |
| authorships[1].affiliations[0].raw_affiliation_string | Department of Electrical and Computer Engineering, Tennessee Technological University, Cookeville, TN, USA |
| authorships[1].institutions[0].id | https://openalex.org/I63920570 |
| authorships[1].institutions[0].ror | https://ror.org/05drmrq39 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I63920570 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | Tennessee Technological University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jonathan J. Sanderson |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Department of Electrical and Computer Engineering, Tennessee Technological University, Cookeville, TN, USA |
| authorships[2].author.id | https://openalex.org/A5070802892 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6199-6249 |
| authorships[2].author.display_name | Tolulope A. Odetola |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I63920570 |
| authorships[2].affiliations[0].raw_affiliation_string | Department of Electrical and Computer Engineering, Tennessee Technological University, Cookeville, TN, USA |
| authorships[2].institutions[0].id | https://openalex.org/I63920570 |
| authorships[2].institutions[0].ror | https://ror.org/05drmrq39 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I63920570 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | Tennessee Technological University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Tolulope A. Odetola |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Department of Electrical and Computer Engineering, Tennessee Technological University, Cookeville, TN, USA |
| authorships[3].author.id | https://openalex.org/A5074265316 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-6263-674X |
| authorships[3].author.display_name | Faiq Khalid |
| authorships[3].countries | AT |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I145847075 |
| authorships[3].affiliations[0].raw_affiliation_string | Department of Computer Engineering, Vienna University of Technology, Wien, Austria |
| authorships[3].institutions[0].id | https://openalex.org/I145847075 |
| authorships[3].institutions[0].ror | https://ror.org/04d836q62 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I145847075 |
| authorships[3].institutions[0].country_code | AT |
| authorships[3].institutions[0].display_name | TU Wien |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Faiq Khalid |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Department of Computer Engineering, Vienna University of Technology, Wien, Austria |
| authorships[4].author.id | https://openalex.org/A5034599612 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0183-8086 |
| authorships[4].author.display_name | Syed Rafay Hasan |
| authorships[4].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I63920570 |
| authorships[4].affiliations[0].raw_affiliation_string | Department of Electrical and Computer Engineering, Tennessee Technological University, Cookeville, TN, USA |
| authorships[4].institutions[0].id | https://openalex.org/I63920570 |
| authorships[4].institutions[0].ror | https://ror.org/05drmrq39 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I63920570 |
| authorships[4].institutions[0].country_code | US |
| authorships[4].institutions[0].display_name | Tennessee Technological University |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Syed Rafay Hasan |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Department of Electrical and Computer Engineering, Tennessee Technological University, Cookeville, TN, USA |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ieeexplore.ieee.org/ielx7/6287639/10005208/10032539.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | StAIn: Stealthy Avenues of Attacks on Horizontally Collaborated Convolutional Neural Network Inference and Their Mitigation |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11689 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 1.0 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Adversarial Robustness in Machine Learning |
| related_works | https://openalex.org/W2502115930, https://openalex.org/W2482350142, https://openalex.org/W4246396837, https://openalex.org/W3126451824, https://openalex.org/W4320018150, https://openalex.org/W4239582170, https://openalex.org/W2918664383, https://openalex.org/W106056076, https://openalex.org/W4320855730, https://openalex.org/W2135200719 |
| cited_by_count | 8 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 3 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 4 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1109/access.2023.3241096 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S2485537415 |
| best_oa_location.source.issn | 2169-3536 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2169-3536 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | IEEE Access |
| best_oa_location.source.host_organization | https://openalex.org/P4310319808 |
| best_oa_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| best_oa_location.source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://ieeexplore.ieee.org/ielx7/6287639/10005208/10032539.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | IEEE Access |
| best_oa_location.landing_page_url | https://doi.org/10.1109/access.2023.3241096 |
| primary_location.id | doi:10.1109/access.2023.3241096 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S2485537415 |
| primary_location.source.issn | 2169-3536 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2169-3536 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | IEEE Access |
| primary_location.source.host_organization | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://ieeexplore.ieee.org/ielx7/6287639/10005208/10032539.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | IEEE Access |
| primary_location.landing_page_url | https://doi.org/10.1109/access.2023.3241096 |
| publication_date | 2023-01-01 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W3116057280, https://openalex.org/W3212789686, https://openalex.org/W6761100157, https://openalex.org/W6764668024, https://openalex.org/W2964082701, https://openalex.org/W2997560666, https://openalex.org/W3110777925, https://openalex.org/W3159010353, https://openalex.org/W2980856918, https://openalex.org/W3200886011, https://openalex.org/W3187219391, https://openalex.org/W3044591330, https://openalex.org/W3016219164, https://openalex.org/W2982595342, https://openalex.org/W3163857190, https://openalex.org/W2612193523, https://openalex.org/W2896180420, https://openalex.org/W2962814013, https://openalex.org/W2896225285, https://openalex.org/W2962883027, https://openalex.org/W3114386910, https://openalex.org/W4249516033, https://openalex.org/W4312813996, https://openalex.org/W2888003123, https://openalex.org/W4242053016, https://openalex.org/W6752346538, https://openalex.org/W2963303354, https://openalex.org/W4246001895, https://openalex.org/W3172552249, https://openalex.org/W3199221149, https://openalex.org/W6779552448, https://openalex.org/W2997572583, https://openalex.org/W6743446608, https://openalex.org/W2996337378, https://openalex.org/W6794699994, https://openalex.org/W2798919674, https://openalex.org/W2898009658, https://openalex.org/W3158689288, https://openalex.org/W4236099117, https://openalex.org/W2809788191, https://openalex.org/W1993211683, https://openalex.org/W3044508112, https://openalex.org/W2899025187, https://openalex.org/W2899111971, https://openalex.org/W2954978443, https://openalex.org/W6796665987, https://openalex.org/W6751982602, https://openalex.org/W6750124314, https://openalex.org/W2620038827, https://openalex.org/W2969695741, https://openalex.org/W6784426856, https://openalex.org/W2205725565, https://openalex.org/W2997532515, https://openalex.org/W6753216052, https://openalex.org/W6756133841, https://openalex.org/W3186971988, https://openalex.org/W6739868092, https://openalex.org/W3084384598, https://openalex.org/W3048697382, https://openalex.org/W2951526967, https://openalex.org/W2968044287, https://openalex.org/W2983498217, https://openalex.org/W3117200447, https://openalex.org/W3174884678, https://openalex.org/W4292070570, https://openalex.org/W6637373629, https://openalex.org/W4287122064, https://openalex.org/W4295897591, https://openalex.org/W1686810756, https://openalex.org/W2963744840, https://openalex.org/W2963703618, https://openalex.org/W2804084874, https://openalex.org/W3105904398, https://openalex.org/W3034754805, https://openalex.org/W4293846201, https://openalex.org/W3092873005, https://openalex.org/W3099502074, https://openalex.org/W4288296135, https://openalex.org/W3105147370, https://openalex.org/W2900778888, https://openalex.org/W3098486933, https://openalex.org/W2963378725, https://openalex.org/W2888394138, https://openalex.org/W4288363925, https://openalex.org/W4287184915 |
| referenced_works_count | 85 |
| abstract_inverted_index.a | 19, 31, 138, 161, 209 |
| abstract_inverted_index.5G | 15 |
| abstract_inverted_index.HC | 42, 74, 257 |
| abstract_inverted_index.In | 84 |
| abstract_inverted_index.To | 237 |
| abstract_inverted_index.We | 114 |
| abstract_inverted_index.an | 44 |
| abstract_inverted_index.as | 107 |
| abstract_inverted_index.be | 82 |
| abstract_inverted_index.by | 227 |
| abstract_inverted_index.in | 4, 73, 111, 255 |
| abstract_inverted_index.is | 29, 108, 169, 221, 244 |
| abstract_inverted_index.of | 21, 41, 68, 78, 104, 137, 205, 213, 240, 253, 262 |
| abstract_inverted_index.on | 132, 197, 215, 235 |
| abstract_inverted_index.to | 9, 57, 65, 121, 142, 186, 223, 233, 269 |
| abstract_inverted_index.we | 87 |
| abstract_inverted_index.CNN | 177, 200 |
| abstract_inverted_index.DLA | 106, 254 |
| abstract_inverted_index.Due | 64 |
| abstract_inverted_index.Map | 157 |
| abstract_inverted_index.Our | 125, 194 |
| abstract_inverted_index.The | 38, 217 |
| abstract_inverted_index.all | 260 |
| abstract_inverted_index.and | 16, 95, 154, 173, 182, 191, 259, 267 |
| abstract_inverted_index.are | 92, 115, 184, 265 |
| abstract_inverted_index.due | 8 |
| abstract_inverted_index.for | 33 |
| abstract_inverted_index.has | 101 |
| abstract_inverted_index.not | 54 |
| abstract_inverted_index.our | 241, 263 |
| abstract_inverted_index.the | 51, 58, 66, 76, 99, 105, 109, 144, 188, 225, 229, 238, 245, 250, 256, 270, 274 |
| abstract_inverted_index.two | 203 |
| abstract_inverted_index.DLA. | 113, 275 |
| abstract_inverted_index.Edge | 35 |
| abstract_inverted_index.Fast | 149 |
| abstract_inverted_index.Four | 175 |
| abstract_inverted_index.With | 0 |
| abstract_inverted_index.able | 222 |
| abstract_inverted_index.also | 116 |
| abstract_inverted_index.back | 232 |
| abstract_inverted_index.best | 239 |
| abstract_inverted_index.case | 110 |
| abstract_inverted_index.deep | 60 |
| abstract_inverted_index.does | 53 |
| abstract_inverted_index.drop | 212 |
| abstract_inverted_index.each | 206 |
| abstract_inverted_index.edge | 23, 71, 140 |
| abstract_inverted_index.even | 97 |
| abstract_inverted_index.four | 198 |
| abstract_inverted_index.have | 55 |
| abstract_inverted_index.link | 12 |
| abstract_inverted_index.maps | 135 |
| abstract_inverted_index.show | 208 |
| abstract_inverted_index.some | 89 |
| abstract_inverted_index.such | 123 |
| abstract_inverted_index.that | 91, 248 |
| abstract_inverted_index.this | 85, 243 |
| abstract_inverted_index.used | 185 |
| abstract_inverted_index.very | 93 |
| abstract_inverted_index.when | 98 |
| abstract_inverted_index.work | 247 |
| abstract_inverted_index.(CNN) | 166 |
| abstract_inverted_index.(D2D) | 6 |
| abstract_inverted_index.(EI). | 37 |
| abstract_inverted_index.(FMs) | 136 |
| abstract_inverted_index.(HC)) | 28 |
| abstract_inverted_index.(e.g. | 148 |
| abstract_inverted_index.(with | 202 |
| abstract_inverted_index.NextG | 17 |
| abstract_inverted_index.based | 167 |
| abstract_inverted_index.first | 246 |
| abstract_inverted_index.local | 129 |
| abstract_inverted_index.novel | 118, 126 |
| abstract_inverted_index.three | 195, 261 |
| abstract_inverted_index.(DLA). | 63 |
| abstract_inverted_index.(FGSM) | 153 |
| abstract_inverted_index.(e.g., | 14 |
| abstract_inverted_index.Attack | 158 |
| abstract_inverted_index.Method | 152 |
| abstract_inverted_index.Signed | 151 |
| abstract_inverted_index.VGG16) | 183 |
| abstract_inverted_index.access | 56 |
| abstract_inverted_index.actual | 230 |
| abstract_inverted_index.attack | 226 |
| abstract_inverted_index.cannot | 81 |
| abstract_inverted_index.device | 141 |
| abstract_inverted_index.entire | 59 |
| abstract_inverted_index.filter | 168 |
| abstract_inverted_index.models | 178, 201 |
| abstract_inverted_index.modify | 143 |
| abstract_inverted_index.nature | 40 |
| abstract_inverted_index.neural | 164 |
| abstract_inverted_index.offers | 43 |
| abstract_inverted_index.output | 133 |
| abstract_inverted_index.paper, | 86 |
| abstract_inverted_index.within | 273 |
| abstract_inverted_index.(LeNet, | 179 |
| abstract_inverted_index.(called | 25 |
| abstract_inverted_index.against | 46 |
| abstract_inverted_index.attack) | 207 |
| abstract_inverted_index.attacks | 49, 90, 127, 147, 190, 196, 264 |
| abstract_inverted_index.because | 50 |
| abstract_inverted_index.defense | 192 |
| abstract_inverted_index.devices | 24, 72, 80 |
| abstract_inverted_index.feature | 134 |
| abstract_inverted_index.methods | 120 |
| abstract_inverted_index.minimal | 102 |
| abstract_inverted_index.network | 165 |
| abstract_inverted_index.reality | 32 |
| abstract_inverted_index.regular | 145 |
| abstract_inverted_index.tested. | 174 |
| abstract_inverted_index.unearth | 88 |
| abstract_inverted_index.(JSMA)). | 159 |
| abstract_inverted_index.Gradient | 150 |
| abstract_inverted_index.HC-based | 112 |
| abstract_inverted_index.Saliency | 156 |
| abstract_inverted_index.accuracy | 211, 231 |
| abstract_inverted_index.agnostic | 268 |
| abstract_inverted_index.approach | 220 |
| abstract_inverted_index.attacker | 100 |
| abstract_inverted_index.attacks. | 124 |
| abstract_inverted_index.average. | 216, 236 |
| abstract_inverted_index.becoming | 30 |
| abstract_inverted_index.capacity | 13 |
| abstract_inverted_index.improved | 10 |
| abstract_inverted_index.learning | 61 |
| abstract_inverted_index.leverage | 128 |
| abstract_inverted_index.location | 272 |
| abstract_inverted_index.mitigate | 122, 224 |
| abstract_inverted_index.multiple | 22, 69 |
| abstract_inverted_index.proposed | 189, 218 |
| abstract_inverted_index.scalable | 266 |
| abstract_inverted_index.security | 251 |
| abstract_inverted_index.stealthy | 96 |
| abstract_inverted_index.targeted | 139 |
| abstract_inverted_index.validate | 187 |
| abstract_inverted_index.wireless | 11 |
| abstract_inverted_index.advantage | 45 |
| abstract_inverted_index.adversary | 52 |
| abstract_inverted_index.available | 131 |
| abstract_inverted_index.designed, | 171 |
| abstract_inverted_index.different | 176, 199 |
| abstract_inverted_index.effective | 94 |
| abstract_inverted_index.filtering | 119, 219 |
| abstract_inverted_index.knowledge | 103 |
| abstract_inverted_index.malicious | 79 |
| abstract_inverted_index.partition | 271 |
| abstract_inverted_index.potential | 2 |
| abstract_inverted_index.providing | 117 |
| abstract_inverted_index.real-time | 34 |
| abstract_inverted_index.systems), | 18 |
| abstract_inverted_index.untrusted | 70 |
| abstract_inverted_index.62% | 214 |
| abstract_inverted_index.Similarly, | 160 |
| abstract_inverted_index.customized | 162 |
| abstract_inverted_index.developed, | 172 |
| abstract_inverted_index.horizontal | 26 |
| abstract_inverted_index.knowledge, | 242 |
| abstract_inverted_index.recovering | 228 |
| abstract_inverted_index.variations | 204 |
| abstract_inverted_index.CapsuleNet, | 180 |
| abstract_inverted_index.MiniVGGNet, | 181 |
| abstract_inverted_index.adversarial | 48, 146 |
| abstract_inverted_index.distributed | 39 |
| abstract_inverted_index.eliminated. | 83 |
| abstract_inverted_index.empirically | 170 |
| abstract_inverted_index.improvement | 3 |
| abstract_inverted_index.information | 130 |
| abstract_inverted_index.involvement | 67 |
| abstract_inverted_index.possibility | 77 |
| abstract_inverted_index.significant | 1 |
| abstract_inverted_index.substantial | 210 |
| abstract_inverted_index.traditional | 47 |
| abstract_inverted_index.75.1% | 234 |
| abstract_inverted_index.Intelligence | 36 |
| abstract_inverted_index.architecture | 62 |
| abstract_inverted_index.environment, | 75, 258 |
| abstract_inverted_index.investigates | 249 |
| abstract_inverted_index.collaboration | 20, 27 |
| abstract_inverted_index.communication | 7 |
| abstract_inverted_index.convolutional | 163 |
| abstract_inverted_index.vulnerability | 252 |
| abstract_inverted_index.Jacobian-based | 155 |
| abstract_inverted_index.methodologies. | 193 |
| abstract_inverted_index.device-to-device | 5 |
| cited_by_percentile_year.max | 97 |
| cited_by_percentile_year.min | 91 |
| countries_distinct_count | 2 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.86202843 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |