Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP Article Swipe
Yang‐Yi Chen
,
Hongcheng Gao
,
Ganqu Cui
,
Fanchao Qi
,
Longtao Huang
,
Zhiyuan Liu
,
Maosong Sun
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2022.emnlp-main.771
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2022.emnlp-main.771
Textual adversarial samples play important roles in multiple subfields of NLP research, including security, evaluation, explainability, and data augmentation. However, most work mixes all these roles, obscuring the problem definitions and research goals of the security role that aims to reveal the practical concerns of NLP models. In this paper, we rethink the research paradigm of textual adversarial samples in security scenarios. We discuss the deficiencies in previous work and propose our suggestions that the research on the Security-oriented adversarial NLP (SoadNLP) should: (1) evaluate their methods on security tasks to demonstrate the real-world concerns; (2) consider real-world attackers' goals, instead of developing impractical methods. To this end, we first collect, process, and release a security datasets collection Advbench. Then, we reformalize the task and adjust the emphasis on different goals in SoadNLP. Next, we propose a simple method based on heuristic rules that can easily fulfill the actual adversarial goals to simulate real-world attack methods. We conduct experiments on both the attack and the defense sides on Advbench. Experimental results show that our method has higher practical value, indicating that the research paradigm in SoadNLP may start from our new benchmark. All the code and data of Advbench can be obtained at https://github.com/thunlp/Advbench.
Related Topics
Concepts
Adversarial system
Computer science
Heuristic
Benchmark (surveying)
Task (project management)
Artificial intelligence
Process (computing)
Code (set theory)
Machine learning
Natural language processing
Data science
Programming language
Set (abstract data type)
Management
Economics
Geodesy
Operating system
Geography
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.18653/v1/2022.emnlp-main.771
- https://aclanthology.org/2022.emnlp-main.771.pdf
- OA Status
- gold
- Cited By
- 23
- References
- 84
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4385573354
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4385573354Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.18653/v1/2022.emnlp-main.771Digital Object Identifier
- Title
-
Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-01-01Full publication date if available
- Authors
-
Yang‐Yi Chen, Hongcheng Gao, Ganqu Cui, Fanchao Qi, Longtao Huang, Zhiyuan Liu, Maosong SunList of authors in order
- Landing page
-
https://doi.org/10.18653/v1/2022.emnlp-main.771Publisher landing page
- PDF URL
-
https://aclanthology.org/2022.emnlp-main.771.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://aclanthology.org/2022.emnlp-main.771.pdfDirect OA link when available
- Concepts
-
Adversarial system, Computer science, Heuristic, Benchmark (surveying), Task (project management), Artificial intelligence, Process (computing), Code (set theory), Machine learning, Natural language processing, Data science, Programming language, Set (abstract data type), Management, Economics, Geodesy, Operating system, GeographyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
23Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 8, 2024: 7, 2023: 8Per-year citation counts (last 5 years)
- References (count)
-
84Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4385573354 |
|---|---|
| doi | https://doi.org/10.18653/v1/2022.emnlp-main.771 |
| ids.doi | https://doi.org/10.18653/v1/2022.emnlp-main.771 |
| ids.openalex | https://openalex.org/W4385573354 |
| fwci | 4.50337287 |
| type | article |
| title | Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP |
| 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 | 0.945900022983551 |
| 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/T10734 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9160000085830688 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1710 |
| topics[1].subfield.display_name | Information Systems |
| topics[1].display_name | Information and Cyber Security |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C37736160 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9461394548416138 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[0].display_name | Adversarial system |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.8076189160346985 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C173801870 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6155582666397095 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q201413 |
| concepts[2].display_name | Heuristic |
| concepts[3].id | https://openalex.org/C185798385 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6148252487182617 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1161707 |
| concepts[3].display_name | Benchmark (surveying) |
| concepts[4].id | https://openalex.org/C2780451532 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5683895945549011 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[4].display_name | Task (project management) |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.524133026599884 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C98045186 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5026471614837646 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q205663 |
| concepts[6].display_name | Process (computing) |
| concepts[7].id | https://openalex.org/C2776760102 |
| concepts[7].level | 3 |
| concepts[7].score | 0.4622378945350647 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q5139990 |
| concepts[7].display_name | Code (set theory) |
| concepts[8].id | https://openalex.org/C119857082 |
| concepts[8].level | 1 |
| concepts[8].score | 0.408689945936203 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[8].display_name | Machine learning |
| concepts[9].id | https://openalex.org/C204321447 |
| concepts[9].level | 1 |
| concepts[9].score | 0.3332633078098297 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[9].display_name | Natural language processing |
| concepts[10].id | https://openalex.org/C2522767166 |
| concepts[10].level | 1 |
| concepts[10].score | 0.32738518714904785 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2374463 |
| concepts[10].display_name | Data science |
| concepts[11].id | https://openalex.org/C199360897 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[11].display_name | Programming language |
| concepts[12].id | https://openalex.org/C177264268 |
| concepts[12].level | 2 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[12].display_name | Set (abstract data type) |
| concepts[13].id | https://openalex.org/C187736073 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[13].display_name | Management |
| concepts[14].id | https://openalex.org/C162324750 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[14].display_name | Economics |
| concepts[15].id | https://openalex.org/C13280743 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q131089 |
| concepts[15].display_name | Geodesy |
| concepts[16].id | https://openalex.org/C111919701 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[16].display_name | Operating system |
| concepts[17].id | https://openalex.org/C205649164 |
| concepts[17].level | 0 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[17].display_name | Geography |
| keywords[0].id | https://openalex.org/keywords/adversarial-system |
| keywords[0].score | 0.9461394548416138 |
| keywords[0].display_name | Adversarial system |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.8076189160346985 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/heuristic |
| keywords[2].score | 0.6155582666397095 |
| keywords[2].display_name | Heuristic |
| keywords[3].id | https://openalex.org/keywords/benchmark |
| keywords[3].score | 0.6148252487182617 |
| keywords[3].display_name | Benchmark (surveying) |
| keywords[4].id | https://openalex.org/keywords/task |
| keywords[4].score | 0.5683895945549011 |
| keywords[4].display_name | Task (project management) |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.524133026599884 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/process |
| keywords[6].score | 0.5026471614837646 |
| keywords[6].display_name | Process (computing) |
| keywords[7].id | https://openalex.org/keywords/code |
| keywords[7].score | 0.4622378945350647 |
| keywords[7].display_name | Code (set theory) |
| keywords[8].id | https://openalex.org/keywords/machine-learning |
| keywords[8].score | 0.408689945936203 |
| keywords[8].display_name | Machine learning |
| keywords[9].id | https://openalex.org/keywords/natural-language-processing |
| keywords[9].score | 0.3332633078098297 |
| keywords[9].display_name | Natural language processing |
| keywords[10].id | https://openalex.org/keywords/data-science |
| keywords[10].score | 0.32738518714904785 |
| keywords[10].display_name | Data science |
| language | en |
| locations[0].id | doi:10.18653/v1/2022.emnlp-main.771 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://aclanthology.org/2022.emnlp-main.771.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-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 | Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing |
| locations[0].landing_page_url | https://doi.org/10.18653/v1/2022.emnlp-main.771 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5005441169 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-8488-635X |
| authorships[0].author.display_name | Yang‐Yi Chen |
| authorships[0].countries | CN, US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I157725225 |
| authorships[0].affiliations[0].raw_affiliation_string | University of Illinois Urbana-Champaign |
| authorships[0].affiliations[1].institution_ids | https://openalex.org/I99065089 |
| authorships[0].affiliations[1].raw_affiliation_string | NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| authorships[0].institutions[0].id | https://openalex.org/I99065089 |
| authorships[0].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Tsinghua University |
| authorships[0].institutions[1].id | https://openalex.org/I157725225 |
| authorships[0].institutions[1].ror | https://ror.org/047426m28 |
| authorships[0].institutions[1].type | education |
| authorships[0].institutions[1].lineage | https://openalex.org/I157725225 |
| authorships[0].institutions[1].country_code | US |
| authorships[0].institutions[1].display_name | University of Illinois Urbana-Champaign |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yangyi Chen |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing, University of Illinois Urbana-Champaign |
| authorships[1].author.id | https://openalex.org/A5110370692 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Hongcheng Gao |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[1].affiliations[0].raw_affiliation_string | NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| authorships[1].affiliations[1].institution_ids | https://openalex.org/I158842170 |
| authorships[1].affiliations[1].raw_affiliation_string | Chongqing University |
| authorships[1].institutions[0].id | https://openalex.org/I158842170 |
| authorships[1].institutions[0].ror | https://ror.org/023rhb549 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I158842170 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Chongqing University |
| authorships[1].institutions[1].id | https://openalex.org/I99065089 |
| authorships[1].institutions[1].ror | https://ror.org/03cve4549 |
| authorships[1].institutions[1].type | education |
| authorships[1].institutions[1].lineage | https://openalex.org/I99065089 |
| authorships[1].institutions[1].country_code | CN |
| authorships[1].institutions[1].display_name | Tsinghua University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Hongcheng Gao |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Chongqing University, NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| authorships[2].author.id | https://openalex.org/A5102542015 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-6385-8547 |
| authorships[2].author.display_name | Ganqu Cui |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[2].affiliations[0].raw_affiliation_string | NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| authorships[2].institutions[0].id | https://openalex.org/I99065089 |
| authorships[2].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Tsinghua University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ganqu Cui |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| authorships[3].author.id | https://openalex.org/A5030183493 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-4400-4033 |
| authorships[3].author.display_name | Fanchao Qi |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[3].affiliations[0].raw_affiliation_string | NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| authorships[3].institutions[0].id | https://openalex.org/I99065089 |
| authorships[3].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Tsinghua University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Fanchao Qi |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| authorships[4].author.id | https://openalex.org/A5058197951 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-0517-1592 |
| authorships[4].author.display_name | Longtao Huang |
| authorships[4].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I4210095624 |
| authorships[4].affiliations[0].raw_affiliation_string | Alibaba Group |
| authorships[4].institutions[0].id | https://openalex.org/I4210095624 |
| authorships[4].institutions[0].ror | https://ror.org/00rn0m335 |
| authorships[4].institutions[0].type | company |
| authorships[4].institutions[0].lineage | https://openalex.org/I4210095624, https://openalex.org/I45928872 |
| authorships[4].institutions[0].country_code | US |
| authorships[4].institutions[0].display_name | Alibaba Group (United States) |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Longtao Huang |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Alibaba Group |
| authorships[5].author.id | https://openalex.org/A5100320723 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-7709-2543 |
| authorships[5].author.display_name | Zhiyuan Liu |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[5].affiliations[0].raw_affiliation_string | NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| authorships[5].affiliations[1].raw_affiliation_string | IICTUS, Shanghai |
| authorships[5].institutions[0].id | https://openalex.org/I99065089 |
| authorships[5].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | Tsinghua University |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Zhiyuan Liu |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | IICTUS, Shanghai, NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| authorships[6].author.id | https://openalex.org/A5046448314 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-6011-6115 |
| authorships[6].author.display_name | Maosong Sun |
| authorships[6].countries | CN |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I99065089 |
| authorships[6].affiliations[0].raw_affiliation_string | NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| authorships[6].affiliations[1].raw_affiliation_string | IICTUS, Shanghai |
| authorships[6].institutions[0].id | https://openalex.org/I99065089 |
| authorships[6].institutions[0].ror | https://ror.org/03cve4549 |
| authorships[6].institutions[0].type | education |
| authorships[6].institutions[0].lineage | https://openalex.org/I99065089 |
| authorships[6].institutions[0].country_code | CN |
| authorships[6].institutions[0].display_name | Tsinghua University |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Maosong Sun |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | IICTUS, Shanghai, NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://aclanthology.org/2022.emnlp-main.771.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP |
| 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 | 0.945900022983551 |
| 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/W4246396837, https://openalex.org/W2482350142, https://openalex.org/W3176240006, https://openalex.org/W3126451824, https://openalex.org/W1561927205, https://openalex.org/W3191453585, https://openalex.org/W4297672492, https://openalex.org/W4288019534, https://openalex.org/W4310988119 |
| cited_by_count | 23 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 8 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 7 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 8 |
| locations_count | 1 |
| best_oa_location.id | doi:10.18653/v1/2022.emnlp-main.771 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://aclanthology.org/2022.emnlp-main.771.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-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 | Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing |
| best_oa_location.landing_page_url | https://doi.org/10.18653/v1/2022.emnlp-main.771 |
| primary_location.id | doi:10.18653/v1/2022.emnlp-main.771 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://aclanthology.org/2022.emnlp-main.771.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-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 | Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing |
| primary_location.landing_page_url | https://doi.org/10.18653/v1/2022.emnlp-main.771 |
| publication_date | 2022-01-01 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W3120706522, https://openalex.org/W2970449623, https://openalex.org/W2394542850, https://openalex.org/W2759820691, https://openalex.org/W3035164976, https://openalex.org/W3183440606, https://openalex.org/W2962818281, https://openalex.org/W3035367371, https://openalex.org/W3172794097, https://openalex.org/W2971196067, https://openalex.org/W2964236337, https://openalex.org/W2949128310, https://openalex.org/W2799194071, https://openalex.org/W3177190797, https://openalex.org/W4385573698, https://openalex.org/W2947415936, https://openalex.org/W2982756474, https://openalex.org/W2514714814, https://openalex.org/W3155936402, https://openalex.org/W3101449015, https://openalex.org/W3046764764, https://openalex.org/W4224903411, https://openalex.org/W2098192829, https://openalex.org/W3203138619, https://openalex.org/W3007121986, https://openalex.org/W4321005039, https://openalex.org/W2792441346, https://openalex.org/W2963834268, https://openalex.org/W3035507081, https://openalex.org/W2908323419, https://openalex.org/W3104423855, https://openalex.org/W2487326407, https://openalex.org/W3176648901, https://openalex.org/W2963942654, https://openalex.org/W3087728626, https://openalex.org/W3170572542, https://openalex.org/W2996851481, https://openalex.org/W2925285378, https://openalex.org/W3007685714, https://openalex.org/W3035736465, https://openalex.org/W2160536005, https://openalex.org/W2047021305, https://openalex.org/W2970078867, https://openalex.org/W2595653137, https://openalex.org/W4205725534, https://openalex.org/W3198659451, https://openalex.org/W2982222442, https://openalex.org/W2966854934, https://openalex.org/W2735135478, https://openalex.org/W3084992427, https://openalex.org/W2888830392, https://openalex.org/W3087231533, https://openalex.org/W4283211054, https://openalex.org/W2917831717, https://openalex.org/W2962718684, https://openalex.org/W2896457183, https://openalex.org/W2984051011, https://openalex.org/W3174848559, https://openalex.org/W4287803080, https://openalex.org/W3037045905, https://openalex.org/W1480224957, https://openalex.org/W3168586460, https://openalex.org/W4293471672, https://openalex.org/W3034408878, https://openalex.org/W3103934057, https://openalex.org/W3205696278, https://openalex.org/W3169948074, https://openalex.org/W2963126845, https://openalex.org/W3035441470, https://openalex.org/W2963969878, https://openalex.org/W2166656775, https://openalex.org/W2925709178, https://openalex.org/W3117433489, https://openalex.org/W3156498837, https://openalex.org/W3001639638, https://openalex.org/W2811010710, https://openalex.org/W2535690855, https://openalex.org/W2027731328, https://openalex.org/W3199704160, https://openalex.org/W3101118235, https://openalex.org/W3196893172, https://openalex.org/W2982054702, https://openalex.org/W3103061166, https://openalex.org/W3098649723 |
| referenced_works_count | 84 |
| abstract_inverted_index.a | 114, 136 |
| abstract_inverted_index.In | 47 |
| abstract_inverted_index.To | 105 |
| abstract_inverted_index.We | 62, 156 |
| abstract_inverted_index.at | 202 |
| abstract_inverted_index.be | 200 |
| abstract_inverted_index.in | 6, 59, 66, 131, 184 |
| abstract_inverted_index.of | 9, 33, 44, 55, 101, 197 |
| abstract_inverted_index.on | 76, 87, 128, 140, 159, 167 |
| abstract_inverted_index.to | 39, 90, 151 |
| abstract_inverted_index.we | 50, 108, 120, 134 |
| abstract_inverted_index.(1) | 83 |
| abstract_inverted_index.(2) | 95 |
| abstract_inverted_index.All | 192 |
| abstract_inverted_index.NLP | 10, 45, 80 |
| abstract_inverted_index.all | 23 |
| abstract_inverted_index.and | 16, 30, 69, 112, 124, 163, 195 |
| abstract_inverted_index.can | 144, 199 |
| abstract_inverted_index.has | 175 |
| abstract_inverted_index.may | 186 |
| abstract_inverted_index.new | 190 |
| abstract_inverted_index.our | 71, 173, 189 |
| abstract_inverted_index.the | 27, 34, 41, 52, 64, 74, 77, 92, 122, 126, 147, 161, 164, 181, 193 |
| abstract_inverted_index.aims | 38 |
| abstract_inverted_index.both | 160 |
| abstract_inverted_index.code | 194 |
| abstract_inverted_index.data | 17, 196 |
| abstract_inverted_index.end, | 107 |
| abstract_inverted_index.from | 188 |
| abstract_inverted_index.most | 20 |
| abstract_inverted_index.play | 3 |
| abstract_inverted_index.role | 36 |
| abstract_inverted_index.show | 171 |
| abstract_inverted_index.task | 123 |
| abstract_inverted_index.that | 37, 73, 143, 172, 180 |
| abstract_inverted_index.this | 48, 106 |
| abstract_inverted_index.work | 21, 68 |
| abstract_inverted_index.Next, | 133 |
| abstract_inverted_index.Then, | 119 |
| abstract_inverted_index.based | 139 |
| abstract_inverted_index.first | 109 |
| abstract_inverted_index.goals | 32, 130, 150 |
| abstract_inverted_index.mixes | 22 |
| abstract_inverted_index.roles | 5 |
| abstract_inverted_index.rules | 142 |
| abstract_inverted_index.sides | 166 |
| abstract_inverted_index.start | 187 |
| abstract_inverted_index.tasks | 89 |
| abstract_inverted_index.their | 85 |
| abstract_inverted_index.these | 24 |
| abstract_inverted_index.actual | 148 |
| abstract_inverted_index.adjust | 125 |
| abstract_inverted_index.attack | 154, 162 |
| abstract_inverted_index.easily | 145 |
| abstract_inverted_index.goals, | 99 |
| abstract_inverted_index.higher | 176 |
| abstract_inverted_index.method | 138, 174 |
| abstract_inverted_index.paper, | 49 |
| abstract_inverted_index.reveal | 40 |
| abstract_inverted_index.roles, | 25 |
| abstract_inverted_index.simple | 137 |
| abstract_inverted_index.value, | 178 |
| abstract_inverted_index.SoadNLP | 185 |
| abstract_inverted_index.Textual | 0 |
| abstract_inverted_index.conduct | 157 |
| abstract_inverted_index.defense | 165 |
| abstract_inverted_index.discuss | 63 |
| abstract_inverted_index.fulfill | 146 |
| abstract_inverted_index.instead | 100 |
| abstract_inverted_index.methods | 86 |
| abstract_inverted_index.models. | 46 |
| abstract_inverted_index.problem | 28 |
| abstract_inverted_index.propose | 70, 135 |
| abstract_inverted_index.release | 113 |
| abstract_inverted_index.results | 170 |
| abstract_inverted_index.rethink | 51 |
| abstract_inverted_index.samples | 2, 58 |
| abstract_inverted_index.should: | 82 |
| abstract_inverted_index.textual | 56 |
| abstract_inverted_index.Advbench | 198 |
| abstract_inverted_index.However, | 19 |
| abstract_inverted_index.SoadNLP. | 132 |
| abstract_inverted_index.collect, | 110 |
| abstract_inverted_index.concerns | 43 |
| abstract_inverted_index.consider | 96 |
| abstract_inverted_index.datasets | 116 |
| abstract_inverted_index.emphasis | 127 |
| abstract_inverted_index.evaluate | 84 |
| abstract_inverted_index.methods. | 104, 155 |
| abstract_inverted_index.multiple | 7 |
| abstract_inverted_index.obtained | 201 |
| abstract_inverted_index.paradigm | 54, 183 |
| abstract_inverted_index.previous | 67 |
| abstract_inverted_index.process, | 111 |
| abstract_inverted_index.research | 31, 53, 75, 182 |
| abstract_inverted_index.security | 35, 60, 88, 115 |
| abstract_inverted_index.simulate | 152 |
| abstract_inverted_index.(SoadNLP) | 81 |
| abstract_inverted_index.Advbench. | 118, 168 |
| abstract_inverted_index.concerns; | 94 |
| abstract_inverted_index.different | 129 |
| abstract_inverted_index.heuristic | 141 |
| abstract_inverted_index.important | 4 |
| abstract_inverted_index.including | 12 |
| abstract_inverted_index.obscuring | 26 |
| abstract_inverted_index.practical | 42, 177 |
| abstract_inverted_index.research, | 11 |
| abstract_inverted_index.security, | 13 |
| abstract_inverted_index.subfields | 8 |
| abstract_inverted_index.attackers' | 98 |
| abstract_inverted_index.benchmark. | 191 |
| abstract_inverted_index.collection | 117 |
| abstract_inverted_index.developing | 102 |
| abstract_inverted_index.indicating | 179 |
| abstract_inverted_index.real-world | 93, 97, 153 |
| abstract_inverted_index.scenarios. | 61 |
| abstract_inverted_index.adversarial | 1, 57, 79, 149 |
| abstract_inverted_index.definitions | 29 |
| abstract_inverted_index.demonstrate | 91 |
| abstract_inverted_index.evaluation, | 14 |
| abstract_inverted_index.experiments | 158 |
| abstract_inverted_index.impractical | 103 |
| abstract_inverted_index.reformalize | 121 |
| abstract_inverted_index.suggestions | 72 |
| abstract_inverted_index.Experimental | 169 |
| abstract_inverted_index.deficiencies | 65 |
| abstract_inverted_index.augmentation. | 18 |
| abstract_inverted_index.explainability, | 15 |
| abstract_inverted_index.Security-oriented | 78 |
| abstract_inverted_index.https://github.com/thunlp/Advbench. | 203 |
| cited_by_percentile_year.max | 99 |
| cited_by_percentile_year.min | 98 |
| countries_distinct_count | 2 |
| institutions_distinct_count | 7 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/17 |
| sustainable_development_goals[0].score | 0.5199999809265137 |
| sustainable_development_goals[0].display_name | Partnerships for the goals |
| citation_normalized_percentile.value | 0.93268118 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |