White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defense Article Swipe
Shahrukh Rafi Khan
,
Mahnoor Shahid
,
Navdeeppal Singh
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2202.05778
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2202.05778
In this work, we evaluate the adversarial robustness of BERT models trained on German Hate Speech datasets. We also complement our evaluation with two novel white-box character and word level attacks thereby contributing to the range of attacks available. Furthermore, we also perform a comparison of two novel character-level defense strategies and evaluate their robustness with one another.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2202.05778
- https://arxiv.org/pdf/2202.05778
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4226366518
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4226366518Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2202.05778Digital Object Identifier
- Title
-
White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level DefenseWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-02-11Full publication date if available
- Authors
-
Shahrukh Rafi Khan, Mahnoor Shahid, Navdeeppal SinghList of authors in order
- Landing page
-
https://arxiv.org/abs/2202.05778Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2202.05778Direct 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/2202.05778Direct OA link when available
- Concepts
-
Robustness (evolution), German, Character (mathematics), Computer science, Adversarial system, Speech recognition, Complement (music), Artificial intelligence, Natural language processing, Linguistics, Mathematics, Complementation, Philosophy, Chemistry, Phenotype, Biochemistry, Gene, GeometryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4226366518 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2202.05778 |
| ids.doi | https://doi.org/10.48550/arxiv.2202.05778 |
| ids.openalex | https://openalex.org/W4226366518 |
| fwci | |
| type | preprint |
| title | White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defense |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12262 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9945999979972839 |
| 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 | Hate Speech and Cyberbullying Detection |
| topics[1].id | https://openalex.org/T10181 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9478999972343445 |
| 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 | Natural Language Processing Techniques |
| topics[2].id | https://openalex.org/T11689 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9180999994277954 |
| 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 | Adversarial Robustness in Machine Learning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C63479239 |
| concepts[0].level | 3 |
| concepts[0].score | 0.790412187576294 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[0].display_name | Robustness (evolution) |
| concepts[1].id | https://openalex.org/C154775046 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7133709192276001 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q188 |
| concepts[1].display_name | German |
| concepts[2].id | https://openalex.org/C2780861071 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6889047622680664 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1062934 |
| concepts[2].display_name | Character (mathematics) |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.6634417772293091 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C37736160 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5450688600540161 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[4].display_name | Adversarial system |
| concepts[5].id | https://openalex.org/C28490314 |
| concepts[5].level | 1 |
| concepts[5].score | 0.4957023859024048 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[5].display_name | Speech recognition |
| concepts[6].id | https://openalex.org/C112313634 |
| concepts[6].level | 5 |
| concepts[6].score | 0.42326200008392334 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7886648 |
| concepts[6].display_name | Complement (music) |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.402340292930603 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C204321447 |
| concepts[8].level | 1 |
| concepts[8].score | 0.3258489668369293 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[8].display_name | Natural language processing |
| concepts[9].id | https://openalex.org/C41895202 |
| concepts[9].level | 1 |
| concepts[9].score | 0.1716192066669464 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[9].display_name | Linguistics |
| concepts[10].id | https://openalex.org/C33923547 |
| concepts[10].level | 0 |
| concepts[10].score | 0.08385443687438965 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[10].display_name | Mathematics |
| concepts[11].id | https://openalex.org/C188082640 |
| concepts[11].level | 4 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q1780899 |
| concepts[11].display_name | Complementation |
| concepts[12].id | https://openalex.org/C138885662 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[12].display_name | Philosophy |
| concepts[13].id | https://openalex.org/C185592680 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[13].display_name | Chemistry |
| concepts[14].id | https://openalex.org/C127716648 |
| concepts[14].level | 3 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q104053 |
| concepts[14].display_name | Phenotype |
| concepts[15].id | https://openalex.org/C55493867 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[15].display_name | Biochemistry |
| concepts[16].id | https://openalex.org/C104317684 |
| concepts[16].level | 2 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[16].display_name | Gene |
| concepts[17].id | https://openalex.org/C2524010 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[17].display_name | Geometry |
| keywords[0].id | https://openalex.org/keywords/robustness |
| keywords[0].score | 0.790412187576294 |
| keywords[0].display_name | Robustness (evolution) |
| keywords[1].id | https://openalex.org/keywords/german |
| keywords[1].score | 0.7133709192276001 |
| keywords[1].display_name | German |
| keywords[2].id | https://openalex.org/keywords/character |
| keywords[2].score | 0.6889047622680664 |
| keywords[2].display_name | Character (mathematics) |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.6634417772293091 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/adversarial-system |
| keywords[4].score | 0.5450688600540161 |
| keywords[4].display_name | Adversarial system |
| keywords[5].id | https://openalex.org/keywords/speech-recognition |
| keywords[5].score | 0.4957023859024048 |
| keywords[5].display_name | Speech recognition |
| keywords[6].id | https://openalex.org/keywords/complement |
| keywords[6].score | 0.42326200008392334 |
| keywords[6].display_name | Complement (music) |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.402340292930603 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/natural-language-processing |
| keywords[8].score | 0.3258489668369293 |
| keywords[8].display_name | Natural language processing |
| keywords[9].id | https://openalex.org/keywords/linguistics |
| keywords[9].score | 0.1716192066669464 |
| keywords[9].display_name | Linguistics |
| keywords[10].id | https://openalex.org/keywords/mathematics |
| keywords[10].score | 0.08385443687438965 |
| keywords[10].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2202.05778 |
| 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/2202.05778 |
| 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/2202.05778 |
| locations[1].id | doi:10.48550/arxiv.2202.05778 |
| 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.2202.05778 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5112479160 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-0722-0044 |
| authorships[0].author.display_name | Shahrukh Rafi Khan |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Khan, Shahrukh |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5056944461 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Mahnoor Shahid |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Shahid, Mahnoor |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5058064819 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2921-4876 |
| authorships[2].author.display_name | Navdeeppal Singh |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Singh, Navdeeppal |
| authorships[2].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2202.05778 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defense |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12262 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9945999979972839 |
| 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 | Hate Speech and Cyberbullying Detection |
| related_works | https://openalex.org/W2502115930, https://openalex.org/W2482350142, https://openalex.org/W4246396837, https://openalex.org/W3176240006, https://openalex.org/W3126451824, https://openalex.org/W2315527029, https://openalex.org/W1561927205, https://openalex.org/W3191453585, https://openalex.org/W4297672492, https://openalex.org/W4288019534 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2202.05778 |
| 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/2202.05778 |
| 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/2202.05778 |
| primary_location.id | pmh:oai:arXiv.org:2202.05778 |
| 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/2202.05778 |
| 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/2202.05778 |
| publication_date | 2022-02-11 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 43 |
| abstract_inverted_index.In | 0 |
| abstract_inverted_index.We | 17 |
| abstract_inverted_index.of | 8, 36, 45 |
| abstract_inverted_index.on | 12 |
| abstract_inverted_index.to | 33 |
| abstract_inverted_index.we | 3, 40 |
| abstract_inverted_index.and | 27, 51 |
| abstract_inverted_index.one | 56 |
| abstract_inverted_index.our | 20 |
| abstract_inverted_index.the | 5, 34 |
| abstract_inverted_index.two | 23, 46 |
| abstract_inverted_index.BERT | 9 |
| abstract_inverted_index.Hate | 14 |
| abstract_inverted_index.also | 18, 41 |
| abstract_inverted_index.this | 1 |
| abstract_inverted_index.with | 22, 55 |
| abstract_inverted_index.word | 28 |
| abstract_inverted_index.level | 29 |
| abstract_inverted_index.novel | 24, 47 |
| abstract_inverted_index.range | 35 |
| abstract_inverted_index.their | 53 |
| abstract_inverted_index.work, | 2 |
| abstract_inverted_index.German | 13 |
| abstract_inverted_index.Speech | 15 |
| abstract_inverted_index.models | 10 |
| abstract_inverted_index.attacks | 30, 37 |
| abstract_inverted_index.defense | 49 |
| abstract_inverted_index.perform | 42 |
| abstract_inverted_index.thereby | 31 |
| abstract_inverted_index.trained | 11 |
| abstract_inverted_index.another. | 57 |
| abstract_inverted_index.evaluate | 4, 52 |
| abstract_inverted_index.character | 26 |
| abstract_inverted_index.datasets. | 16 |
| abstract_inverted_index.white-box | 25 |
| abstract_inverted_index.available. | 38 |
| abstract_inverted_index.comparison | 44 |
| abstract_inverted_index.complement | 19 |
| abstract_inverted_index.evaluation | 21 |
| abstract_inverted_index.robustness | 7, 54 |
| abstract_inverted_index.strategies | 50 |
| abstract_inverted_index.adversarial | 6 |
| abstract_inverted_index.Furthermore, | 39 |
| abstract_inverted_index.contributing | 32 |
| abstract_inverted_index.character-level | 48 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.7099999785423279 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile |