Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for Text Classification and Text Regression Article Swipe
Yidong Chai
,
Ruicheng Liang
,
Sagar Samtani
,
Hongyi Zhu
,
Meng Wang
,
Yezheng Liu
,
Yuanchun Jiang
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.36227/techrxiv.17185568
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.36227/techrxiv.17185568
Deep learning (DL) models have significantly improved the performance of text classification and text regression tasks. However, DL models are often strikingly vulnerable to adversarial attacks. Many researchers have aimed to develop adversarial attacks against DL models in realistic black-box settings (i.e., assumes no model knowledge is accessible to attackers) that typically operate with a two-phase framework: (1) sensitivity estimation through gradient-based or deletion-based methods to evaluate the sensitivity of each token to the prediction of the target model, and (2) perturbation execution to craft adversarial examples based on the estimated token sensitivity. However, gradient-based and deletion-based methods used to estimate sensitivity often face issues of capturing the directionality of tokens and overlapping token sensitivities, respectively. In this study, we propose a novel eXplanation-based method for Adversarial Text Attacks (XATA) that leverages additive feature attribution explainable methods, namely LIME or SHAP, to measure the sensitivity of input tokens when crafting black-box adversarial attacks on DL models performing text classification or text regression. We evaluated XATA’s attack performance on DL models executing text classification on three datasets (IMDB Movie Review, Yelp Reviews-Polarity, and Amazon Reviews-Polarity) and DL models conducting text regression on three datasets (My Personality, Drug Review, and CommonLit Readability). The proposed XATA outperformed the existing gradient-based and deletion-based adversarial attack baselines in both tasks. These findings indicate that the ever-growing research focused on improving the explainability of DL models with additive feature attribution explainable methods can provide attackers with weapons to launch targeted adversarial attacks.
Related Topics
Concepts
Security token
Computer science
Adversarial system
Artificial intelligence
Regression
Machine learning
Feature (linguistics)
Deep learning
Sensitivity (control systems)
Natural language processing
Data mining
Statistics
Mathematics
Engineering
Philosophy
Computer security
Electronic engineering
Linguistics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.36227/techrxiv.17185568
- https://www.techrxiv.org/articles/preprint/Local_Post-hoc_Explainable_Methods_for_Adversarial_Text_Attacks/17185568/2/files/35256706.pdf
- OA Status
- gold
- Cited By
- 2
- References
- 37
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4200276198
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4200276198Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.36227/techrxiv.17185568Digital Object Identifier
- Title
-
Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for Text Classification and Text RegressionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-12-21Full publication date if available
- Authors
-
Yidong Chai, Ruicheng Liang, Sagar Samtani, Hongyi Zhu, Meng Wang, Yezheng Liu, Yuanchun JiangList of authors in order
- Landing page
-
https://doi.org/10.36227/techrxiv.17185568Publisher landing page
- PDF URL
-
https://www.techrxiv.org/articles/preprint/Local_Post-hoc_Explainable_Methods_for_Adversarial_Text_Attacks/17185568/2/files/35256706.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://www.techrxiv.org/articles/preprint/Local_Post-hoc_Explainable_Methods_for_Adversarial_Text_Attacks/17185568/2/files/35256706.pdfDirect OA link when available
- Concepts
-
Security token, Computer science, Adversarial system, Artificial intelligence, Regression, Machine learning, Feature (linguistics), Deep learning, Sensitivity (control systems), Natural language processing, Data mining, Statistics, Mathematics, Engineering, Philosophy, Computer security, Electronic engineering, LinguisticsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 2Per-year citation counts (last 5 years)
- References (count)
-
37Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4200276198 |
|---|---|
| doi | https://doi.org/10.36227/techrxiv.17185568 |
| ids.doi | https://doi.org/10.36227/techrxiv.17185568 |
| ids.openalex | https://openalex.org/W4200276198 |
| fwci | 0.28220715 |
| type | preprint |
| title | Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for Text Classification and Text Regression |
| 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 | 0.9975000023841858 |
| 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/T12026 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9320999979972839 |
| 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 | Explainable Artificial Intelligence (XAI) |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C48145219 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7318756580352783 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1335365 |
| concepts[0].display_name | Security token |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7213572859764099 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C37736160 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7041265368461609 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1801315 |
| concepts[2].display_name | Adversarial system |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.6608502864837646 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C83546350 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5793201923370361 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1139051 |
| concepts[4].display_name | Regression |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5291536450386047 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C2776401178 |
| concepts[6].level | 2 |
| concepts[6].score | 0.507230281829834 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[6].display_name | Feature (linguistics) |
| concepts[7].id | https://openalex.org/C108583219 |
| concepts[7].level | 2 |
| concepts[7].score | 0.47545167803764343 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[7].display_name | Deep learning |
| concepts[8].id | https://openalex.org/C21200559 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4747198820114136 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7451068 |
| concepts[8].display_name | Sensitivity (control systems) |
| concepts[9].id | https://openalex.org/C204321447 |
| concepts[9].level | 1 |
| concepts[9].score | 0.4003438353538513 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[9].display_name | Natural language processing |
| concepts[10].id | https://openalex.org/C124101348 |
| concepts[10].level | 1 |
| concepts[10].score | 0.33099639415740967 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q172491 |
| concepts[10].display_name | Data mining |
| concepts[11].id | https://openalex.org/C105795698 |
| concepts[11].level | 1 |
| concepts[11].score | 0.10967037081718445 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[11].display_name | Statistics |
| concepts[12].id | https://openalex.org/C33923547 |
| concepts[12].level | 0 |
| concepts[12].score | 0.10086232423782349 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[12].display_name | Mathematics |
| concepts[13].id | https://openalex.org/C127413603 |
| concepts[13].level | 0 |
| concepts[13].score | 0.07607927918434143 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[13].display_name | Engineering |
| concepts[14].id | https://openalex.org/C138885662 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[14].display_name | Philosophy |
| concepts[15].id | https://openalex.org/C38652104 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[15].display_name | Computer security |
| concepts[16].id | https://openalex.org/C24326235 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q126095 |
| concepts[16].display_name | Electronic engineering |
| concepts[17].id | https://openalex.org/C41895202 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[17].display_name | Linguistics |
| keywords[0].id | https://openalex.org/keywords/security-token |
| keywords[0].score | 0.7318756580352783 |
| keywords[0].display_name | Security token |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7213572859764099 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/adversarial-system |
| keywords[2].score | 0.7041265368461609 |
| keywords[2].display_name | Adversarial system |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.6608502864837646 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/regression |
| keywords[4].score | 0.5793201923370361 |
| keywords[4].display_name | Regression |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.5291536450386047 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/feature |
| keywords[6].score | 0.507230281829834 |
| keywords[6].display_name | Feature (linguistics) |
| keywords[7].id | https://openalex.org/keywords/deep-learning |
| keywords[7].score | 0.47545167803764343 |
| keywords[7].display_name | Deep learning |
| keywords[8].id | https://openalex.org/keywords/sensitivity |
| keywords[8].score | 0.4747198820114136 |
| keywords[8].display_name | Sensitivity (control systems) |
| keywords[9].id | https://openalex.org/keywords/natural-language-processing |
| keywords[9].score | 0.4003438353538513 |
| keywords[9].display_name | Natural language processing |
| keywords[10].id | https://openalex.org/keywords/data-mining |
| keywords[10].score | 0.33099639415740967 |
| keywords[10].display_name | Data mining |
| keywords[11].id | https://openalex.org/keywords/statistics |
| keywords[11].score | 0.10967037081718445 |
| keywords[11].display_name | Statistics |
| keywords[12].id | https://openalex.org/keywords/mathematics |
| keywords[12].score | 0.10086232423782349 |
| keywords[12].display_name | Mathematics |
| keywords[13].id | https://openalex.org/keywords/engineering |
| keywords[13].score | 0.07607927918434143 |
| keywords[13].display_name | Engineering |
| language | en |
| locations[0].id | doi:10.36227/techrxiv.17185568 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.techrxiv.org/articles/preprint/Local_Post-hoc_Explainable_Methods_for_Adversarial_Text_Attacks/17185568/2/files/35256706.pdf |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.36227/techrxiv.17185568 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5030014366 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-0260-7589 |
| authorships[0].author.display_name | Yidong Chai |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yidong Chai |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5025447683 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6266-2657 |
| authorships[1].author.display_name | Ruicheng Liang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Ruicheng Liang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5038811607 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-4513-805X |
| authorships[2].author.display_name | Sagar Samtani |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Sagar Samtani |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5004908593 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-9643-0790 |
| authorships[3].author.display_name | Hongyi Zhu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Hongyi Zhu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100377147 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-3094-7735 |
| authorships[4].author.display_name | Meng Wang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Meng Wang |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5030946475 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-9193-5236 |
| authorships[5].author.display_name | Yezheng Liu |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Yezheng Liu |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5004103125 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-0886-3647 |
| authorships[6].author.display_name | Yuanchun Jiang |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Yuanchun Jiang |
| 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://www.techrxiv.org/articles/preprint/Local_Post-hoc_Explainable_Methods_for_Adversarial_Text_Attacks/17185568/2/files/35256706.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for Text Classification and Text Regression |
| 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 | 0.9975000023841858 |
| 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 | 2 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 2 |
| locations_count | 1 |
| best_oa_location.id | doi:10.36227/techrxiv.17185568 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.techrxiv.org/articles/preprint/Local_Post-hoc_Explainable_Methods_for_Adversarial_Text_Attacks/17185568/2/files/35256706.pdf |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.36227/techrxiv.17185568 |
| primary_location.id | doi:10.36227/techrxiv.17185568 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.techrxiv.org/articles/preprint/Local_Post-hoc_Explainable_Methods_for_Adversarial_Text_Attacks/17185568/2/files/35256706.pdf |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.36227/techrxiv.17185568 |
| publication_date | 2021-12-21 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2609368435, https://openalex.org/W2788403449, https://openalex.org/W2962907114, https://openalex.org/W2963834268, https://openalex.org/W2964060211, https://openalex.org/W3203135439, https://openalex.org/W2996851481, https://openalex.org/W2962862931, https://openalex.org/W1522301498, https://openalex.org/W2981220581, https://openalex.org/W2516809705, https://openalex.org/W3015177564, https://openalex.org/W2605409611, https://openalex.org/W3174150157, https://openalex.org/W2408141691, https://openalex.org/W4287639392, https://openalex.org/W3105640742, https://openalex.org/W3216683580, https://openalex.org/W2996061341, https://openalex.org/W3015001695, https://openalex.org/W2994506732, https://openalex.org/W3101449015, https://openalex.org/W2551974706, https://openalex.org/W1945616565, https://openalex.org/W2958089299, https://openalex.org/W2806246579, https://openalex.org/W2603766943, https://openalex.org/W2949128310, https://openalex.org/W2923325523, https://openalex.org/W2799194071, https://openalex.org/W3021395787, https://openalex.org/W2962818281, https://openalex.org/W3200913691, https://openalex.org/W3117433489, https://openalex.org/W3104423855, https://openalex.org/W2963859254, https://openalex.org/W4288104702 |
| referenced_works_count | 37 |
| abstract_inverted_index.a | 55, 122 |
| abstract_inverted_index.DL | 18, 36, 155, 169, 186, 229 |
| abstract_inverted_index.In | 117 |
| abstract_inverted_index.We | 163 |
| abstract_inverted_index.in | 38, 213 |
| abstract_inverted_index.is | 47 |
| abstract_inverted_index.no | 44 |
| abstract_inverted_index.of | 10, 70, 76, 106, 110, 146, 228 |
| abstract_inverted_index.on | 89, 154, 168, 174, 191, 224 |
| abstract_inverted_index.or | 63, 140, 160 |
| abstract_inverted_index.to | 24, 31, 49, 66, 73, 84, 100, 142, 242 |
| abstract_inverted_index.we | 120 |
| abstract_inverted_index.(1) | 58 |
| abstract_inverted_index.(2) | 81 |
| abstract_inverted_index.(My | 194 |
| abstract_inverted_index.The | 201 |
| abstract_inverted_index.and | 13, 80, 96, 112, 182, 185, 198, 208 |
| abstract_inverted_index.are | 20 |
| abstract_inverted_index.can | 237 |
| abstract_inverted_index.for | 126 |
| abstract_inverted_index.the | 8, 68, 74, 77, 90, 108, 144, 205, 220, 226 |
| abstract_inverted_index.(DL) | 3 |
| abstract_inverted_index.Deep | 1 |
| abstract_inverted_index.Drug | 196 |
| abstract_inverted_index.LIME | 139 |
| abstract_inverted_index.Many | 27 |
| abstract_inverted_index.Text | 128 |
| abstract_inverted_index.XATA | 203 |
| abstract_inverted_index.Yelp | 180 |
| abstract_inverted_index.both | 214 |
| abstract_inverted_index.each | 71 |
| abstract_inverted_index.face | 104 |
| abstract_inverted_index.have | 5, 29 |
| abstract_inverted_index.text | 11, 14, 158, 161, 172, 189 |
| abstract_inverted_index.that | 51, 131, 219 |
| abstract_inverted_index.this | 118 |
| abstract_inverted_index.used | 99 |
| abstract_inverted_index.when | 149 |
| abstract_inverted_index.with | 54, 231, 240 |
| abstract_inverted_index.(IMDB | 177 |
| abstract_inverted_index.Movie | 178 |
| abstract_inverted_index.SHAP, | 141 |
| abstract_inverted_index.These | 216 |
| abstract_inverted_index.aimed | 30 |
| abstract_inverted_index.based | 88 |
| abstract_inverted_index.craft | 85 |
| abstract_inverted_index.input | 147 |
| abstract_inverted_index.model | 45 |
| abstract_inverted_index.novel | 123 |
| abstract_inverted_index.often | 21, 103 |
| abstract_inverted_index.three | 175, 192 |
| abstract_inverted_index.token | 72, 92, 114 |
| abstract_inverted_index.(XATA) | 130 |
| abstract_inverted_index.(i.e., | 42 |
| abstract_inverted_index.Amazon | 183 |
| abstract_inverted_index.attack | 166, 211 |
| abstract_inverted_index.issues | 105 |
| abstract_inverted_index.launch | 243 |
| abstract_inverted_index.method | 125 |
| abstract_inverted_index.model, | 79 |
| abstract_inverted_index.models | 4, 19, 37, 156, 170, 187, 230 |
| abstract_inverted_index.namely | 138 |
| abstract_inverted_index.study, | 119 |
| abstract_inverted_index.target | 78 |
| abstract_inverted_index.tasks. | 16, 215 |
| abstract_inverted_index.tokens | 111, 148 |
| abstract_inverted_index.Attacks | 129 |
| abstract_inverted_index.Review, | 179, 197 |
| abstract_inverted_index.against | 35 |
| abstract_inverted_index.assumes | 43 |
| abstract_inverted_index.attacks | 34, 153 |
| abstract_inverted_index.develop | 32 |
| abstract_inverted_index.feature | 134, 233 |
| abstract_inverted_index.focused | 223 |
| abstract_inverted_index.measure | 143 |
| abstract_inverted_index.methods | 65, 98, 236 |
| abstract_inverted_index.operate | 53 |
| abstract_inverted_index.propose | 121 |
| abstract_inverted_index.provide | 238 |
| abstract_inverted_index.through | 61 |
| abstract_inverted_index.weapons | 241 |
| abstract_inverted_index.However, | 17, 94 |
| abstract_inverted_index.XATA’s | 165 |
| abstract_inverted_index.additive | 133, 232 |
| abstract_inverted_index.attacks. | 26, 246 |
| abstract_inverted_index.crafting | 150 |
| abstract_inverted_index.datasets | 176, 193 |
| abstract_inverted_index.estimate | 101 |
| abstract_inverted_index.evaluate | 67 |
| abstract_inverted_index.examples | 87 |
| abstract_inverted_index.existing | 206 |
| abstract_inverted_index.findings | 217 |
| abstract_inverted_index.improved | 7 |
| abstract_inverted_index.indicate | 218 |
| abstract_inverted_index.learning | 2 |
| abstract_inverted_index.methods, | 137 |
| abstract_inverted_index.proposed | 202 |
| abstract_inverted_index.research | 222 |
| abstract_inverted_index.settings | 41 |
| abstract_inverted_index.targeted | 244 |
| abstract_inverted_index.<p> | 0 |
| abstract_inverted_index.CommonLit | 199 |
| abstract_inverted_index.attackers | 239 |
| abstract_inverted_index.baselines | 212 |
| abstract_inverted_index.black-box | 40, 151 |
| abstract_inverted_index.capturing | 107 |
| abstract_inverted_index.estimated | 91 |
| abstract_inverted_index.evaluated | 164 |
| abstract_inverted_index.executing | 171 |
| abstract_inverted_index.execution | 83 |
| abstract_inverted_index.improving | 225 |
| abstract_inverted_index.knowledge | 46 |
| abstract_inverted_index.leverages | 132 |
| abstract_inverted_index.realistic | 39 |
| abstract_inverted_index.two-phase | 56 |
| abstract_inverted_index.typically | 52 |
| abstract_inverted_index.</p> | 247 |
| abstract_inverted_index.accessible | 48 |
| abstract_inverted_index.attackers) | 50 |
| abstract_inverted_index.conducting | 188 |
| abstract_inverted_index.estimation | 60 |
| abstract_inverted_index.framework: | 57 |
| abstract_inverted_index.performing | 157 |
| abstract_inverted_index.prediction | 75 |
| abstract_inverted_index.regression | 15, 190 |
| abstract_inverted_index.strikingly | 22 |
| abstract_inverted_index.vulnerable | 23 |
| abstract_inverted_index.Adversarial | 127 |
| abstract_inverted_index.adversarial | 25, 33, 86, 152, 210, 245 |
| abstract_inverted_index.attribution | 135, 234 |
| abstract_inverted_index.explainable | 136, 235 |
| abstract_inverted_index.overlapping | 113 |
| abstract_inverted_index.performance | 9, 167 |
| abstract_inverted_index.regression. | 162 |
| abstract_inverted_index.researchers | 28 |
| abstract_inverted_index.sensitivity | 59, 69, 102, 145 |
| abstract_inverted_index.Personality, | 195 |
| abstract_inverted_index.ever-growing | 221 |
| abstract_inverted_index.outperformed | 204 |
| abstract_inverted_index.perturbation | 82 |
| abstract_inverted_index.sensitivity. | 93 |
| abstract_inverted_index.Readability). | 200 |
| abstract_inverted_index.respectively. | 116 |
| abstract_inverted_index.significantly | 6 |
| abstract_inverted_index.classification | 12, 159, 173 |
| abstract_inverted_index.deletion-based | 64, 97, 209 |
| abstract_inverted_index.directionality | 109 |
| abstract_inverted_index.explainability | 227 |
| abstract_inverted_index.gradient-based | 62, 95, 207 |
| abstract_inverted_index.sensitivities, | 115 |
| abstract_inverted_index.Reviews-Polarity) | 184 |
| abstract_inverted_index.Reviews-Polarity, | 181 |
| abstract_inverted_index.eXplanation-based | 124 |
| cited_by_percentile_year.max | 96 |
| cited_by_percentile_year.min | 94 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.550000011920929 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile.value | 0.65765026 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |