Resilient automatic model selection for mobility prediction Article Swipe
Syafiq Al Atiiq
,
Christian Gehrmann
,
Karim Khalil
,
Jakob Sternby
,
Yachao Yuan
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1007/s10586-025-05661-x
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1007/s10586-025-05661-x
In order to avoid extensive machine learning models selection and optimizations, Automated Machine Learning (AutoML) has arisen as a practical and efficient way to apply machine learning to many different application areas. Data poisoning is a real threat to the accuracy of machine learning models in different settings, and it has in recent research studies been shown that the usage of AutoML can be even more sensitive to data poisoning than is the case for non-AutoML generated models. On the other hand, the usage of AutoML also has the potential of improving the robustness of a model by adapting the model to adversarial patterns. In this way, good accuracy can be maintained despite the attacker’s efforts to poison the data. However, no previous studies have investigated these effects. In this paper, we examine the risks associated with adversarial trajectory attacks in mobile systems, specifically looking into mobility prediction problems. By using mobility data from two different simulation frameworks: a simulator developed by Ericsson, which is based on a real-world deployment of Airtel’s open-network topology, and the ONE framework, we investigate three different AutoML frameworks and how the mobility accuracy for the frameworks is affected by a mobile trajectory attack. Our results show that re-running AutoML at every retraining is vulnerable to adversarial mobility poisoning and shows high accuracy variance. By contrast, using a single, well-chosen model from an initial AutoML search achieves more stable performance across adversarial conditions, even when the training set includes up to 10% adversarial mobility data.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1007/s10586-025-05661-x
- https://link.springer.com/content/pdf/10.1007/s10586-025-05661-x.pdf
- OA Status
- hybrid
- References
- 46
- OpenAlex ID
- https://openalex.org/W4415292824
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415292824Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1007/s10586-025-05661-xDigital Object Identifier
- Title
-
Resilient automatic model selection for mobility predictionWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-10-17Full publication date if available
- Authors
-
Syafiq Al Atiiq, Christian Gehrmann, Karim Khalil, Jakob Sternby, Yachao YuanList of authors in order
- Landing page
-
https://doi.org/10.1007/s10586-025-05661-xPublisher landing page
- PDF URL
-
https://link.springer.com/content/pdf/10.1007/s10586-025-05661-x.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://link.springer.com/content/pdf/10.1007/s10586-025-05661-x.pdfDirect OA link when available
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
46Number of works referenced by this work
Full payload
| id | https://openalex.org/W4415292824 |
|---|---|
| doi | https://doi.org/10.1007/s10586-025-05661-x |
| ids.doi | https://doi.org/10.1007/s10586-025-05661-x |
| ids.openalex | https://openalex.org/W4415292824 |
| fwci | 0.0 |
| type | article |
| title | Resilient automatic model selection for mobility prediction |
| biblio.issue | 16 |
| biblio.volume | 28 |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11980 |
| topics[0].field.id | https://openalex.org/fields/33 |
| topics[0].field.display_name | Social Sciences |
| topics[0].score | 0.9997000098228455 |
| topics[0].domain.id | https://openalex.org/domains/2 |
| topics[0].domain.display_name | Social Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3313 |
| topics[0].subfield.display_name | Transportation |
| topics[0].display_name | Human Mobility and Location-Based Analysis |
| topics[1].id | https://openalex.org/T11344 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9979000091552734 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2215 |
| topics[1].subfield.display_name | Building and Construction |
| topics[1].display_name | Traffic Prediction and Management Techniques |
| topics[2].id | https://openalex.org/T10761 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9922999739646912 |
| 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 | Vehicular Ad Hoc Networks (VANETs) |
| is_xpac | False |
| apc_list.value | 2190 |
| apc_list.currency | EUR |
| apc_list.value_usd | 2790 |
| apc_paid.value | 2190 |
| apc_paid.currency | EUR |
| apc_paid.value_usd | 2790 |
| language | en |
| locations[0].id | doi:10.1007/s10586-025-05661-x |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S106148199 |
| locations[0].source.issn | 1386-7857, 1573-7543 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 1386-7857 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Cluster Computing |
| locations[0].source.host_organization | https://openalex.org/P4310319900 |
| locations[0].source.host_organization_name | Springer Science+Business Media |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319900, https://openalex.org/P4310319965 |
| locations[0].source.host_organization_lineage_names | Springer Science+Business Media, Springer Nature |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://link.springer.com/content/pdf/10.1007/s10586-025-05661-x.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 | Cluster Computing |
| locations[0].landing_page_url | https://doi.org/10.1007/s10586-025-05661-x |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5008594126 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-8771-7893 |
| authorships[0].author.display_name | Syafiq Al Atiiq |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Syafiq Al Atiiq |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5044464349 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8003-200X |
| authorships[1].author.display_name | Christian Gehrmann |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Christian Gehrmann |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5042169748 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Karim Khalil |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Karim Khalil |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5072803919 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Jakob Sternby |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jakob Sternby |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5032004495 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-7498-002X |
| authorships[4].author.display_name | Yachao Yuan |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Yachao Yuan |
| authorships[4].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://link.springer.com/content/pdf/10.1007/s10586-025-05661-x.pdf |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-18T00:00:00 |
| display_name | Resilient automatic model selection for mobility prediction |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-12-04T23:47:47.292601 |
| primary_topic.id | https://openalex.org/T11980 |
| primary_topic.field.id | https://openalex.org/fields/33 |
| primary_topic.field.display_name | Social Sciences |
| primary_topic.score | 0.9997000098228455 |
| primary_topic.domain.id | https://openalex.org/domains/2 |
| primary_topic.domain.display_name | Social Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3313 |
| primary_topic.subfield.display_name | Transportation |
| primary_topic.display_name | Human Mobility and Location-Based Analysis |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1007/s10586-025-05661-x |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S106148199 |
| best_oa_location.source.issn | 1386-7857, 1573-7543 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 1386-7857 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Cluster Computing |
| best_oa_location.source.host_organization | https://openalex.org/P4310319900 |
| best_oa_location.source.host_organization_name | Springer Science+Business Media |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310319900, https://openalex.org/P4310319965 |
| best_oa_location.source.host_organization_lineage_names | Springer Science+Business Media, Springer Nature |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://link.springer.com/content/pdf/10.1007/s10586-025-05661-x.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 | Cluster Computing |
| best_oa_location.landing_page_url | https://doi.org/10.1007/s10586-025-05661-x |
| primary_location.id | doi:10.1007/s10586-025-05661-x |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S106148199 |
| primary_location.source.issn | 1386-7857, 1573-7543 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 1386-7857 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Cluster Computing |
| primary_location.source.host_organization | https://openalex.org/P4310319900 |
| primary_location.source.host_organization_name | Springer Science+Business Media |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319900, https://openalex.org/P4310319965 |
| primary_location.source.host_organization_lineage_names | Springer Science+Business Media, Springer Nature |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://link.springer.com/content/pdf/10.1007/s10586-025-05661-x.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 | Cluster Computing |
| primary_location.landing_page_url | https://doi.org/10.1007/s10586-025-05661-x |
| publication_date | 2025-10-17 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4394927283, https://openalex.org/W2966284335, https://openalex.org/W4294643306, https://openalex.org/W4403390926, https://openalex.org/W3201904098, https://openalex.org/W4281682675, https://openalex.org/W2102539288, https://openalex.org/W2949676527, https://openalex.org/W3175611124, https://openalex.org/W3211155214, https://openalex.org/W3117793303, https://openalex.org/W2192203593, https://openalex.org/W2895303784, https://openalex.org/W2261198379, https://openalex.org/W2042441131, https://openalex.org/W2169082916, https://openalex.org/W1964461063, https://openalex.org/W2003257780, https://openalex.org/W2807391700, https://openalex.org/W2908595264, https://openalex.org/W2753140366, https://openalex.org/W3134356777, https://openalex.org/W3127304128, https://openalex.org/W3124426233, https://openalex.org/W3166424533, https://openalex.org/W4220654399, https://openalex.org/W4206573673, https://openalex.org/W2111072639, https://openalex.org/W1972243012, https://openalex.org/W3115714663, https://openalex.org/W4323340212, https://openalex.org/W2942091739, https://openalex.org/W2753783305, https://openalex.org/W3103836116, https://openalex.org/W2535690855, https://openalex.org/W2110868467, https://openalex.org/W3192770481, https://openalex.org/W2224750461, https://openalex.org/W2962763344, https://openalex.org/W4399784953, https://openalex.org/W4399119578, https://openalex.org/W2294912729, https://openalex.org/W3217016897, https://openalex.org/W2143548801, https://openalex.org/W2971981784, https://openalex.org/W9657784 |
| referenced_works_count | 46 |
| abstract_inverted_index.a | 19, 36, 96, 159, 168, 196, 223 |
| abstract_inverted_index.By | 150, 220 |
| abstract_inverted_index.In | 1, 105, 129 |
| abstract_inverted_index.On | 79 |
| abstract_inverted_index.an | 228 |
| abstract_inverted_index.as | 18 |
| abstract_inverted_index.at | 206 |
| abstract_inverted_index.be | 64, 111 |
| abstract_inverted_index.by | 98, 162, 195 |
| abstract_inverted_index.in | 46, 52, 141 |
| abstract_inverted_index.is | 35, 72, 165, 193, 209 |
| abstract_inverted_index.it | 50 |
| abstract_inverted_index.no | 122 |
| abstract_inverted_index.of | 42, 61, 85, 91, 95, 171 |
| abstract_inverted_index.on | 167 |
| abstract_inverted_index.to | 3, 24, 28, 39, 68, 102, 117, 211, 246 |
| abstract_inverted_index.up | 245 |
| abstract_inverted_index.we | 132, 179 |
| abstract_inverted_index.10% | 247 |
| abstract_inverted_index.ONE | 177 |
| abstract_inverted_index.Our | 200 |
| abstract_inverted_index.and | 10, 21, 49, 175, 185, 215 |
| abstract_inverted_index.can | 63, 110 |
| abstract_inverted_index.for | 75, 190 |
| abstract_inverted_index.has | 16, 51, 88 |
| abstract_inverted_index.how | 186 |
| abstract_inverted_index.set | 243 |
| abstract_inverted_index.the | 40, 59, 73, 80, 83, 89, 93, 100, 114, 119, 134, 176, 187, 191, 241 |
| abstract_inverted_index.two | 155 |
| abstract_inverted_index.way | 23 |
| abstract_inverted_index.Data | 33 |
| abstract_inverted_index.also | 87 |
| abstract_inverted_index.been | 56 |
| abstract_inverted_index.case | 74 |
| abstract_inverted_index.data | 69, 153 |
| abstract_inverted_index.even | 65, 239 |
| abstract_inverted_index.from | 154, 227 |
| abstract_inverted_index.good | 108 |
| abstract_inverted_index.have | 125 |
| abstract_inverted_index.high | 217 |
| abstract_inverted_index.into | 146 |
| abstract_inverted_index.many | 29 |
| abstract_inverted_index.more | 66, 233 |
| abstract_inverted_index.real | 37 |
| abstract_inverted_index.show | 202 |
| abstract_inverted_index.than | 71 |
| abstract_inverted_index.that | 58, 203 |
| abstract_inverted_index.this | 106, 130 |
| abstract_inverted_index.way, | 107 |
| abstract_inverted_index.when | 240 |
| abstract_inverted_index.with | 137 |
| abstract_inverted_index.apply | 25 |
| abstract_inverted_index.avoid | 4 |
| abstract_inverted_index.based | 166 |
| abstract_inverted_index.data. | 120, 250 |
| abstract_inverted_index.every | 207 |
| abstract_inverted_index.hand, | 82 |
| abstract_inverted_index.model | 97, 101, 226 |
| abstract_inverted_index.order | 2 |
| abstract_inverted_index.other | 81 |
| abstract_inverted_index.risks | 135 |
| abstract_inverted_index.shown | 57 |
| abstract_inverted_index.shows | 216 |
| abstract_inverted_index.these | 127 |
| abstract_inverted_index.three | 181 |
| abstract_inverted_index.usage | 60, 84 |
| abstract_inverted_index.using | 151, 222 |
| abstract_inverted_index.which | 164 |
| abstract_inverted_index.AutoML | 62, 86, 183, 205, 230 |
| abstract_inverted_index.across | 236 |
| abstract_inverted_index.areas. | 32 |
| abstract_inverted_index.arisen | 17 |
| abstract_inverted_index.mobile | 142, 197 |
| abstract_inverted_index.models | 8, 45 |
| abstract_inverted_index.paper, | 131 |
| abstract_inverted_index.poison | 118 |
| abstract_inverted_index.recent | 53 |
| abstract_inverted_index.search | 231 |
| abstract_inverted_index.stable | 234 |
| abstract_inverted_index.threat | 38 |
| abstract_inverted_index.Machine | 13 |
| abstract_inverted_index.attack. | 199 |
| abstract_inverted_index.attacks | 140 |
| abstract_inverted_index.despite | 113 |
| abstract_inverted_index.efforts | 116 |
| abstract_inverted_index.examine | 133 |
| abstract_inverted_index.initial | 229 |
| abstract_inverted_index.looking | 145 |
| abstract_inverted_index.machine | 6, 26, 43 |
| abstract_inverted_index.models. | 78 |
| abstract_inverted_index.results | 201 |
| abstract_inverted_index.single, | 224 |
| abstract_inverted_index.studies | 55, 124 |
| abstract_inverted_index.(AutoML) | 15 |
| abstract_inverted_index.Abstract | 0 |
| abstract_inverted_index.However, | 121 |
| abstract_inverted_index.Learning | 14 |
| abstract_inverted_index.accuracy | 41, 109, 189, 218 |
| abstract_inverted_index.achieves | 232 |
| abstract_inverted_index.adapting | 99 |
| abstract_inverted_index.affected | 194 |
| abstract_inverted_index.effects. | 128 |
| abstract_inverted_index.includes | 244 |
| abstract_inverted_index.learning | 7, 27, 44 |
| abstract_inverted_index.mobility | 147, 152, 188, 213, 249 |
| abstract_inverted_index.previous | 123 |
| abstract_inverted_index.research | 54 |
| abstract_inverted_index.systems, | 143 |
| abstract_inverted_index.training | 242 |
| abstract_inverted_index.Automated | 12 |
| abstract_inverted_index.Ericsson, | 163 |
| abstract_inverted_index.contrast, | 221 |
| abstract_inverted_index.developed | 161 |
| abstract_inverted_index.different | 30, 47, 156, 182 |
| abstract_inverted_index.efficient | 22 |
| abstract_inverted_index.extensive | 5 |
| abstract_inverted_index.generated | 77 |
| abstract_inverted_index.improving | 92 |
| abstract_inverted_index.patterns. | 104 |
| abstract_inverted_index.poisoning | 34, 70, 214 |
| abstract_inverted_index.potential | 90 |
| abstract_inverted_index.practical | 20 |
| abstract_inverted_index.problems. | 149 |
| abstract_inverted_index.selection | 9 |
| abstract_inverted_index.sensitive | 67 |
| abstract_inverted_index.settings, | 48 |
| abstract_inverted_index.simulator | 160 |
| abstract_inverted_index.topology, | 174 |
| abstract_inverted_index.variance. | 219 |
| abstract_inverted_index.Airtel’s | 172 |
| abstract_inverted_index.associated | 136 |
| abstract_inverted_index.deployment | 170 |
| abstract_inverted_index.framework, | 178 |
| abstract_inverted_index.frameworks | 184, 192 |
| abstract_inverted_index.maintained | 112 |
| abstract_inverted_index.non-AutoML | 76 |
| abstract_inverted_index.prediction | 148 |
| abstract_inverted_index.re-running | 204 |
| abstract_inverted_index.real-world | 169 |
| abstract_inverted_index.retraining | 208 |
| abstract_inverted_index.robustness | 94 |
| abstract_inverted_index.simulation | 157 |
| abstract_inverted_index.trajectory | 139, 198 |
| abstract_inverted_index.vulnerable | 210 |
| abstract_inverted_index.adversarial | 103, 138, 212, 237, 248 |
| abstract_inverted_index.application | 31 |
| abstract_inverted_index.conditions, | 238 |
| abstract_inverted_index.frameworks: | 158 |
| abstract_inverted_index.investigate | 180 |
| abstract_inverted_index.performance | 235 |
| abstract_inverted_index.well-chosen | 225 |
| abstract_inverted_index.attacker’s | 115 |
| abstract_inverted_index.investigated | 126 |
| abstract_inverted_index.open-network | 173 |
| abstract_inverted_index.specifically | 144 |
| abstract_inverted_index.optimizations, | 11 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.44575908 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |