Human-Imperceptible Physical Adversarial Attack for NIR Face Recognition Models Article Swipe
Songyan Xie
,
Jinghang Wen
,
Eileen Lee Ming Su
,
Qiucheng Yu
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2504.15823
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2504.15823
Near-infrared (NIR) face recognition systems, which can operate effectively in low-light conditions or in the presence of makeup, exhibit vulnerabilities when subjected to physical adversarial attacks. To further demonstrate the potential risks in real-world applications, we design a novel, stealthy, and practical adversarial patch to attack NIR face recognition systems in a black-box setting. We achieved this by utilizing human-imperceptible infrared-absorbing ink to generate multiple patches with digitally optimized shapes and positions for infrared images. To address the optimization mismatch between digital and real-world NIR imaging, we develop a light reflection model for human skin to minimize pixel-level discrepancies by simulating NIR light reflection. Compared to state-of-the-art (SOTA) physical attacks on NIR face recognition systems, the experimental results show that our method improves the attack success rate in both digital and physical domains, particularly maintaining effectiveness across various face postures. Notably, the proposed approach outperforms SOTA methods, achieving an average attack success rate of 82.46% in the physical domain across different models, compared to 64.18% for existing methods. The artifact is available at https://anonymous.4open.science/r/Human-imperceptible-adversarial-patch-0703/.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2504.15823
- https://arxiv.org/pdf/2504.15823
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4414634046
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414634046Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2504.15823Digital Object Identifier
- Title
-
Human-Imperceptible Physical Adversarial Attack for NIR Face Recognition ModelsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-04-22Full publication date if available
- Authors
-
Songyan Xie, Jinghang Wen, Eileen Lee Ming Su, Qiucheng YuList of authors in order
- Landing page
-
https://arxiv.org/abs/2504.15823Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2504.15823Direct 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/2504.15823Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4414634046 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2504.15823 |
| ids.doi | https://doi.org/10.48550/arxiv.2504.15823 |
| ids.openalex | https://openalex.org/W4414634046 |
| fwci | 0.0 |
| type | preprint |
| title | Human-Imperceptible Physical Adversarial Attack for NIR Face Recognition Models |
| 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 | 0.998199999332428 |
| 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/T10828 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9589999914169312 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1711 |
| topics[1].subfield.display_name | Signal Processing |
| topics[1].display_name | Biometric Identification and Security |
| topics[2].id | https://openalex.org/T11512 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9526000022888184 |
| 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 | Anomaly Detection Techniques and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2504.15823 |
| 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/2504.15823 |
| 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/2504.15823 |
| locations[1].id | doi:10.48550/arxiv.2504.15823 |
| 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.2504.15823 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100937318 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Songyan Xie |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xie, Songyan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5025755329 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5815-4633 |
| authorships[1].author.display_name | Jinghang Wen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wen, Jinghang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5070995732 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-9366-5404 |
| authorships[2].author.display_name | Eileen Lee Ming Su |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Su, Encheng |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5102970603 |
| authorships[3].author.orcid | https://orcid.org/0009-0008-7150-371X |
| authorships[3].author.display_name | Qiucheng Yu |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Yu, Qiucheng |
| authorships[3].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/2504.15823 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Human-Imperceptible Physical Adversarial Attack for NIR Face Recognition Models |
| 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 | 0.998199999332428 |
| 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 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2504.15823 |
| 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/2504.15823 |
| 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/2504.15823 |
| primary_location.id | pmh:oai:arXiv.org:2504.15823 |
| 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/2504.15823 |
| 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/2504.15823 |
| publication_date | 2025-04-22 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 37, 51, 88 |
| abstract_inverted_index.To | 26, 75 |
| abstract_inverted_index.We | 54 |
| abstract_inverted_index.an | 148 |
| abstract_inverted_index.at | 172 |
| abstract_inverted_index.by | 57, 99 |
| abstract_inverted_index.in | 9, 13, 32, 50, 127, 155 |
| abstract_inverted_index.is | 170 |
| abstract_inverted_index.of | 16, 153 |
| abstract_inverted_index.on | 110 |
| abstract_inverted_index.or | 12 |
| abstract_inverted_index.to | 22, 44, 62, 95, 105, 163 |
| abstract_inverted_index.we | 35, 86 |
| abstract_inverted_index.NIR | 46, 84, 101, 111 |
| abstract_inverted_index.The | 168 |
| abstract_inverted_index.and | 40, 70, 82, 130 |
| abstract_inverted_index.can | 6 |
| abstract_inverted_index.for | 72, 92, 165 |
| abstract_inverted_index.ink | 61 |
| abstract_inverted_index.our | 120 |
| abstract_inverted_index.the | 14, 29, 77, 115, 123, 141, 156 |
| abstract_inverted_index.SOTA | 145 |
| abstract_inverted_index.both | 128 |
| abstract_inverted_index.face | 2, 47, 112, 138 |
| abstract_inverted_index.rate | 126, 152 |
| abstract_inverted_index.show | 118 |
| abstract_inverted_index.skin | 94 |
| abstract_inverted_index.that | 119 |
| abstract_inverted_index.this | 56 |
| abstract_inverted_index.when | 20 |
| abstract_inverted_index.with | 66 |
| abstract_inverted_index.(NIR) | 1 |
| abstract_inverted_index.human | 93 |
| abstract_inverted_index.light | 89, 102 |
| abstract_inverted_index.model | 91 |
| abstract_inverted_index.patch | 43 |
| abstract_inverted_index.risks | 31 |
| abstract_inverted_index.which | 5 |
| abstract_inverted_index.(SOTA) | 107 |
| abstract_inverted_index.64.18% | 164 |
| abstract_inverted_index.82.46% | 154 |
| abstract_inverted_index.across | 136, 159 |
| abstract_inverted_index.attack | 45, 124, 150 |
| abstract_inverted_index.design | 36 |
| abstract_inverted_index.domain | 158 |
| abstract_inverted_index.method | 121 |
| abstract_inverted_index.novel, | 38 |
| abstract_inverted_index.shapes | 69 |
| abstract_inverted_index.address | 76 |
| abstract_inverted_index.attacks | 109 |
| abstract_inverted_index.average | 149 |
| abstract_inverted_index.between | 80 |
| abstract_inverted_index.develop | 87 |
| abstract_inverted_index.digital | 81, 129 |
| abstract_inverted_index.exhibit | 18 |
| abstract_inverted_index.further | 27 |
| abstract_inverted_index.images. | 74 |
| abstract_inverted_index.makeup, | 17 |
| abstract_inverted_index.models, | 161 |
| abstract_inverted_index.operate | 7 |
| abstract_inverted_index.patches | 65 |
| abstract_inverted_index.results | 117 |
| abstract_inverted_index.success | 125, 151 |
| abstract_inverted_index.systems | 49 |
| abstract_inverted_index.various | 137 |
| abstract_inverted_index.Compared | 104 |
| abstract_inverted_index.Notably, | 140 |
| abstract_inverted_index.achieved | 55 |
| abstract_inverted_index.approach | 143 |
| abstract_inverted_index.artifact | 169 |
| abstract_inverted_index.attacks. | 25 |
| abstract_inverted_index.compared | 162 |
| abstract_inverted_index.domains, | 132 |
| abstract_inverted_index.existing | 166 |
| abstract_inverted_index.generate | 63 |
| abstract_inverted_index.imaging, | 85 |
| abstract_inverted_index.improves | 122 |
| abstract_inverted_index.infrared | 73 |
| abstract_inverted_index.methods, | 146 |
| abstract_inverted_index.methods. | 167 |
| abstract_inverted_index.minimize | 96 |
| abstract_inverted_index.mismatch | 79 |
| abstract_inverted_index.multiple | 64 |
| abstract_inverted_index.physical | 23, 108, 131, 157 |
| abstract_inverted_index.presence | 15 |
| abstract_inverted_index.proposed | 142 |
| abstract_inverted_index.setting. | 53 |
| abstract_inverted_index.systems, | 4, 114 |
| abstract_inverted_index.achieving | 147 |
| abstract_inverted_index.available | 171 |
| abstract_inverted_index.black-box | 52 |
| abstract_inverted_index.different | 160 |
| abstract_inverted_index.digitally | 67 |
| abstract_inverted_index.low-light | 10 |
| abstract_inverted_index.optimized | 68 |
| abstract_inverted_index.positions | 71 |
| abstract_inverted_index.postures. | 139 |
| abstract_inverted_index.potential | 30 |
| abstract_inverted_index.practical | 41 |
| abstract_inverted_index.stealthy, | 39 |
| abstract_inverted_index.subjected | 21 |
| abstract_inverted_index.utilizing | 58 |
| abstract_inverted_index.conditions | 11 |
| abstract_inverted_index.real-world | 33, 83 |
| abstract_inverted_index.reflection | 90 |
| abstract_inverted_index.simulating | 100 |
| abstract_inverted_index.adversarial | 24, 42 |
| abstract_inverted_index.demonstrate | 28 |
| abstract_inverted_index.effectively | 8 |
| abstract_inverted_index.maintaining | 134 |
| abstract_inverted_index.outperforms | 144 |
| abstract_inverted_index.pixel-level | 97 |
| abstract_inverted_index.recognition | 3, 48, 113 |
| abstract_inverted_index.reflection. | 103 |
| abstract_inverted_index.experimental | 116 |
| abstract_inverted_index.optimization | 78 |
| abstract_inverted_index.particularly | 133 |
| abstract_inverted_index.Near-infrared | 0 |
| abstract_inverted_index.applications, | 34 |
| abstract_inverted_index.discrepancies | 98 |
| abstract_inverted_index.effectiveness | 135 |
| abstract_inverted_index.vulnerabilities | 19 |
| abstract_inverted_index.state-of-the-art | 106 |
| abstract_inverted_index.infrared-absorbing | 60 |
| abstract_inverted_index.human-imperceptible | 59 |
| abstract_inverted_index.https://anonymous.4open.science/r/Human-imperceptible-adversarial-patch-0703/. | 173 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |