Task-Agnostic Detector for Insertion-Based Backdoor Attacks Article Swipe
Weimin Lyu
,
Xiao Lin
,
Songzhu Zheng
,
Lu Pang
,
Haibin Ling
,
Susmit Jha
,
Chao Chen
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.17155
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.17155
Textual backdoor attacks pose significant security threats. Current detection approaches, typically relying on intermediate feature representation or reconstructing potential triggers, are task-specific and less effective beyond sentence classification, struggling with tasks like question answering and named entity recognition. We introduce TABDet (Task-Agnostic Backdoor Detector), a pioneering task-agnostic method for backdoor detection. TABDet leverages final layer logits combined with an efficient pooling technique, enabling unified logit representation across three prominent NLP tasks. TABDet can jointly learn from diverse task-specific models, demonstrating superior detection efficacy over traditional task-specific methods.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2403.17155
- https://arxiv.org/pdf/2403.17155
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4393283820
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4393283820Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2403.17155Digital Object Identifier
- Title
-
Task-Agnostic Detector for Insertion-Based Backdoor AttacksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-03-25Full publication date if available
- Authors
-
Weimin Lyu, Xiao Lin, Songzhu Zheng, Lu Pang, Haibin Ling, Susmit Jha, Chao ChenList of authors in order
- Landing page
-
https://arxiv.org/abs/2403.17155Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2403.17155Direct 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/2403.17155Direct OA link when available
- Concepts
-
Backdoor, Task (project management), Computer science, Computer security, Detector, Arithmetic, Artificial intelligence, Psychology, Mathematics, Telecommunications, Economics, ManagementTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4393283820 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2403.17155 |
| ids.doi | https://doi.org/10.48550/arxiv.2403.17155 |
| ids.openalex | https://openalex.org/W4393283820 |
| fwci | |
| type | preprint |
| title | Task-Agnostic Detector for Insertion-Based Backdoor Attacks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11241 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9872999787330627 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1711 |
| topics[0].subfield.display_name | Signal Processing |
| topics[0].display_name | Advanced Malware Detection Techniques |
| topics[1].id | https://openalex.org/T11424 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9799000024795532 |
| 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 | Security and Verification in Computing |
| topics[2].id | https://openalex.org/T10400 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9426000118255615 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1705 |
| topics[2].subfield.display_name | Computer Networks and Communications |
| topics[2].display_name | Network Security and Intrusion Detection |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2781045450 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9916473627090454 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q254569 |
| concepts[0].display_name | Backdoor |
| concepts[1].id | https://openalex.org/C2780451532 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7517385482788086 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[1].display_name | Task (project management) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.5732690095901489 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C38652104 |
| concepts[3].level | 1 |
| concepts[3].score | 0.50926673412323 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[3].display_name | Computer security |
| concepts[4].id | https://openalex.org/C94915269 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4845220446586609 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1834857 |
| concepts[4].display_name | Detector |
| concepts[5].id | https://openalex.org/C94375191 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3781334161758423 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11205 |
| concepts[5].display_name | Arithmetic |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3346950113773346 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C15744967 |
| concepts[7].level | 0 |
| concepts[7].score | 0.3259124457836151 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[7].display_name | Psychology |
| concepts[8].id | https://openalex.org/C33923547 |
| concepts[8].level | 0 |
| concepts[8].score | 0.18667832016944885 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[8].display_name | Mathematics |
| concepts[9].id | https://openalex.org/C76155785 |
| concepts[9].level | 1 |
| concepts[9].score | 0.11920031905174255 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[9].display_name | Telecommunications |
| concepts[10].id | https://openalex.org/C162324750 |
| concepts[10].level | 0 |
| concepts[10].score | 0.08664000034332275 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[10].display_name | Economics |
| concepts[11].id | https://openalex.org/C187736073 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0584489107131958 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[11].display_name | Management |
| keywords[0].id | https://openalex.org/keywords/backdoor |
| keywords[0].score | 0.9916473627090454 |
| keywords[0].display_name | Backdoor |
| keywords[1].id | https://openalex.org/keywords/task |
| keywords[1].score | 0.7517385482788086 |
| keywords[1].display_name | Task (project management) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.5732690095901489 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/computer-security |
| keywords[3].score | 0.50926673412323 |
| keywords[3].display_name | Computer security |
| keywords[4].id | https://openalex.org/keywords/detector |
| keywords[4].score | 0.4845220446586609 |
| keywords[4].display_name | Detector |
| keywords[5].id | https://openalex.org/keywords/arithmetic |
| keywords[5].score | 0.3781334161758423 |
| keywords[5].display_name | Arithmetic |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.3346950113773346 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/psychology |
| keywords[7].score | 0.3259124457836151 |
| keywords[7].display_name | Psychology |
| keywords[8].id | https://openalex.org/keywords/mathematics |
| keywords[8].score | 0.18667832016944885 |
| keywords[8].display_name | Mathematics |
| keywords[9].id | https://openalex.org/keywords/telecommunications |
| keywords[9].score | 0.11920031905174255 |
| keywords[9].display_name | Telecommunications |
| keywords[10].id | https://openalex.org/keywords/economics |
| keywords[10].score | 0.08664000034332275 |
| keywords[10].display_name | Economics |
| keywords[11].id | https://openalex.org/keywords/management |
| keywords[11].score | 0.0584489107131958 |
| keywords[11].display_name | Management |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2403.17155 |
| 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/2403.17155 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| 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/2403.17155 |
| locations[1].id | doi:10.48550/arxiv.2403.17155 |
| 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.2403.17155 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5073186182 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4991-5466 |
| authorships[0].author.display_name | Weimin Lyu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Lyu, Weimin |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100450531 |
| authorships[1].author.orcid | https://orcid.org/0009-0006-8716-2601 |
| authorships[1].author.display_name | Xiao Lin |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lin, Xiao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5073393494 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Songzhu Zheng |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zheng, Songzhu |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5002808652 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3059-5936 |
| authorships[3].author.display_name | Lu Pang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Pang, Lu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5061469520 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-4094-8413 |
| authorships[4].author.display_name | Haibin Ling |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ling, Haibin |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5035902535 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-5983-9095 |
| authorships[5].author.display_name | Susmit Jha |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Jha, Susmit |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5100408399 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-2094-9734 |
| authorships[6].author.display_name | Chao Chen |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Chen, Chao |
| authorships[6].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/2403.17155 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Task-Agnostic Detector for Insertion-Based Backdoor Attacks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11241 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9872999787330627 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1711 |
| primary_topic.subfield.display_name | Signal Processing |
| primary_topic.display_name | Advanced Malware Detection Techniques |
| related_works | https://openalex.org/W4320031223, https://openalex.org/W3015678314, https://openalex.org/W4281902577, https://openalex.org/W4200629851, https://openalex.org/W3009072493, https://openalex.org/W4386185023, https://openalex.org/W4317672133, https://openalex.org/W3140988292, https://openalex.org/W4386080799, https://openalex.org/W4309417370 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2403.17155 |
| 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/2403.17155 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| 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/2403.17155 |
| primary_location.id | pmh:oai:arXiv.org:2403.17155 |
| 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/2403.17155 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| 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/2403.17155 |
| publication_date | 2024-03-25 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 44 |
| abstract_inverted_index.We | 38 |
| abstract_inverted_index.an | 58 |
| abstract_inverted_index.on | 12 |
| abstract_inverted_index.or | 16 |
| abstract_inverted_index.NLP | 69 |
| abstract_inverted_index.and | 22, 34 |
| abstract_inverted_index.are | 20 |
| abstract_inverted_index.can | 72 |
| abstract_inverted_index.for | 48 |
| abstract_inverted_index.from | 75 |
| abstract_inverted_index.less | 23 |
| abstract_inverted_index.like | 31 |
| abstract_inverted_index.over | 83 |
| abstract_inverted_index.pose | 3 |
| abstract_inverted_index.with | 29, 57 |
| abstract_inverted_index.final | 53 |
| abstract_inverted_index.layer | 54 |
| abstract_inverted_index.learn | 74 |
| abstract_inverted_index.logit | 64 |
| abstract_inverted_index.named | 35 |
| abstract_inverted_index.tasks | 30 |
| abstract_inverted_index.three | 67 |
| abstract_inverted_index.TABDet | 40, 51, 71 |
| abstract_inverted_index.across | 66 |
| abstract_inverted_index.beyond | 25 |
| abstract_inverted_index.entity | 36 |
| abstract_inverted_index.logits | 55 |
| abstract_inverted_index.method | 47 |
| abstract_inverted_index.tasks. | 70 |
| abstract_inverted_index.Current | 7 |
| abstract_inverted_index.Textual | 0 |
| abstract_inverted_index.attacks | 2 |
| abstract_inverted_index.diverse | 76 |
| abstract_inverted_index.feature | 14 |
| abstract_inverted_index.jointly | 73 |
| abstract_inverted_index.models, | 78 |
| abstract_inverted_index.pooling | 60 |
| abstract_inverted_index.relying | 11 |
| abstract_inverted_index.unified | 63 |
| abstract_inverted_index.Backdoor | 42 |
| abstract_inverted_index.backdoor | 1, 49 |
| abstract_inverted_index.combined | 56 |
| abstract_inverted_index.efficacy | 82 |
| abstract_inverted_index.enabling | 62 |
| abstract_inverted_index.methods. | 86 |
| abstract_inverted_index.question | 32 |
| abstract_inverted_index.security | 5 |
| abstract_inverted_index.sentence | 26 |
| abstract_inverted_index.superior | 80 |
| abstract_inverted_index.threats. | 6 |
| abstract_inverted_index.answering | 33 |
| abstract_inverted_index.detection | 8, 81 |
| abstract_inverted_index.effective | 24 |
| abstract_inverted_index.efficient | 59 |
| abstract_inverted_index.introduce | 39 |
| abstract_inverted_index.leverages | 52 |
| abstract_inverted_index.potential | 18 |
| abstract_inverted_index.prominent | 68 |
| abstract_inverted_index.triggers, | 19 |
| abstract_inverted_index.typically | 10 |
| abstract_inverted_index.Detector), | 43 |
| abstract_inverted_index.detection. | 50 |
| abstract_inverted_index.pioneering | 45 |
| abstract_inverted_index.struggling | 28 |
| abstract_inverted_index.technique, | 61 |
| abstract_inverted_index.approaches, | 9 |
| abstract_inverted_index.significant | 4 |
| abstract_inverted_index.traditional | 84 |
| abstract_inverted_index.intermediate | 13 |
| abstract_inverted_index.recognition. | 37 |
| abstract_inverted_index.demonstrating | 79 |
| abstract_inverted_index.task-agnostic | 46 |
| abstract_inverted_index.task-specific | 21, 77, 85 |
| abstract_inverted_index.(Task-Agnostic | 41 |
| abstract_inverted_index.reconstructing | 17 |
| abstract_inverted_index.representation | 15, 65 |
| abstract_inverted_index.classification, | 27 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |