Natural attack for pre-trained models of code Article Swipe
Zhou Yang
,
Jieke Shi
,
Junda He
,
David Lo
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1145/3510003.3510146
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1145/3510003.3510146
Pre-trained models of code have achieved success in many important software\nengineering tasks. However, these powerful models are vulnerable to adversarial\nattacks that slightly perturb model inputs to make a victim model produce wrong\noutputs. Current works mainly attack models of code with examples that preserve\noperational program semantics but ignore a fundamental requirement for\nadversarial example generation: perturbations should be natural to human\njudges, which we refer to as naturalness requirement.\n In this paper, we propose ALERT (nAturaLnEss AwaRe ATtack), a black-box\nattack that adversarially transforms inputs to make victim models produce wrong\noutputs. Different from prior works, this paper considers the natural semantic\nof generated examples at the same time as preserving the operational semantic\nof original inputs. Our user study demonstrates that human developers\nconsistently consider that adversarial examples generated by ALERT are more\nnatural than those generated by the state-of-the-art work by Zhang et al. that\nignores the naturalness requirement. On attacking CodeBERT, our approach can\nachieve attack success rates of 53.62%, 27.79%, and 35.78% across three\ndownstream tasks: vulnerability prediction, clone detection and code authorship\nattribution. On GraphCodeBERT, our approach can achieve average success rates\nof 76.95%, 7.96% and 61.47% on the three tasks. The above outperforms the\nbaseline by 14.07% and 18.56% on the two pre-trained models on average.\nFinally, we investigated the value of the generated adversarial examples to\nharden victim models through an adversarial fine-tuning procedure and\ndemonstrated the accuracy of CodeBERT and GraphCodeBERT against ALERT-generated\nadversarial examples increased by 87.59% and 92.32%, respectively.\n
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1145/3510003.3510146
- OA Status
- green
- Cited By
- 130
- References
- 63
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4220722393
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4220722393Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1145/3510003.3510146Digital Object Identifier
- Title
-
Natural attack for pre-trained models of codeWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-05-21Full publication date if available
- Authors
-
Zhou Yang, Jieke Shi, Junda He, David LoList of authors in order
- Landing page
-
https://doi.org/10.1145/3510003.3510146Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2201.08698Direct OA link when available
- Concepts
-
Computer science, Code (set theory), Natural (archaeology), Programming language, History, Set (abstract data type), ArchaeologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
130Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 37, 2024: 47, 2023: 39, 2022: 7Per-year citation counts (last 5 years)
- References (count)
-
63Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4220722393 |
|---|---|
| doi | https://doi.org/10.1145/3510003.3510146 |
| ids.doi | https://doi.org/10.1145/3510003.3510146 |
| ids.openalex | https://openalex.org/W4220722393 |
| fwci | 18.23432344 |
| type | article |
| title | Natural attack for pre-trained models of code |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 1493 |
| biblio.first_page | 1482 |
| 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 | 0.9993000030517578 |
| 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/T10260 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9983000159263611 |
| 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 | Software Engineering Research |
| topics[2].id | https://openalex.org/T10743 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9944999814033508 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1712 |
| topics[2].subfield.display_name | Software |
| topics[2].display_name | Software Testing and Debugging Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7074094414710999 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2776760102 |
| concepts[1].level | 3 |
| concepts[1].score | 0.5360136032104492 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q5139990 |
| concepts[1].display_name | Code (set theory) |
| concepts[2].id | https://openalex.org/C2776608160 |
| concepts[2].level | 2 |
| concepts[2].score | 0.4974227249622345 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q4785462 |
| concepts[2].display_name | Natural (archaeology) |
| concepts[3].id | https://openalex.org/C199360897 |
| concepts[3].level | 1 |
| concepts[3].score | 0.3656480312347412 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[3].display_name | Programming language |
| concepts[4].id | https://openalex.org/C95457728 |
| concepts[4].level | 0 |
| concepts[4].score | 0.05668339133262634 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q309 |
| concepts[4].display_name | History |
| concepts[5].id | https://openalex.org/C177264268 |
| concepts[5].level | 2 |
| concepts[5].score | 0.0 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[5].display_name | Set (abstract data type) |
| concepts[6].id | https://openalex.org/C166957645 |
| concepts[6].level | 1 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q23498 |
| concepts[6].display_name | Archaeology |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7074094414710999 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/code |
| keywords[1].score | 0.5360136032104492 |
| keywords[1].display_name | Code (set theory) |
| keywords[2].id | https://openalex.org/keywords/natural |
| keywords[2].score | 0.4974227249622345 |
| keywords[2].display_name | Natural (archaeology) |
| keywords[3].id | https://openalex.org/keywords/programming-language |
| keywords[3].score | 0.3656480312347412 |
| keywords[3].display_name | Programming language |
| keywords[4].id | https://openalex.org/keywords/history |
| keywords[4].score | 0.05668339133262634 |
| keywords[4].display_name | History |
| language | en |
| locations[0].id | doi:10.1145/3510003.3510146 |
| locations[0].is_oa | False |
| locations[0].source.id | https://openalex.org/S4363608872 |
| locations[0].source.issn | |
| locations[0].source.type | conference |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the 44th International Conference on Software Engineering |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the 44th International Conference on Software Engineering |
| locations[0].landing_page_url | https://doi.org/10.1145/3510003.3510146 |
| locations[1].id | pmh:oai:arXiv.org:2201.08698 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | https://arxiv.org/pdf/2201.08698 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | text |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://arxiv.org/abs/2201.08698 |
| indexed_in | arxiv, crossref |
| authorships[0].author.id | https://openalex.org/A5008695791 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-5938-1918 |
| authorships[0].author.display_name | Zhou Yang |
| authorships[0].countries | SG |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I79891267 |
| authorships[0].affiliations[0].raw_affiliation_string | Singapore Management University |
| authorships[0].institutions[0].id | https://openalex.org/I79891267 |
| authorships[0].institutions[0].ror | https://ror.org/050qmg959 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I79891267 |
| authorships[0].institutions[0].country_code | SG |
| authorships[0].institutions[0].display_name | Singapore Management University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhou Yang |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Singapore Management University |
| authorships[1].author.id | https://openalex.org/A5002667771 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-0799-5018 |
| authorships[1].author.display_name | Jieke Shi |
| authorships[1].countries | SG |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I79891267 |
| authorships[1].affiliations[0].raw_affiliation_string | Singapore Management University |
| authorships[1].institutions[0].id | https://openalex.org/I79891267 |
| authorships[1].institutions[0].ror | https://ror.org/050qmg959 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I79891267 |
| authorships[1].institutions[0].country_code | SG |
| authorships[1].institutions[0].display_name | Singapore Management University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jieke Shi |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Singapore Management University |
| authorships[2].author.id | https://openalex.org/A5103075577 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-3370-8585 |
| authorships[2].author.display_name | Junda He |
| authorships[2].countries | SG |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I79891267 |
| authorships[2].affiliations[0].raw_affiliation_string | Singapore Management University |
| authorships[2].institutions[0].id | https://openalex.org/I79891267 |
| authorships[2].institutions[0].ror | https://ror.org/050qmg959 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I79891267 |
| authorships[2].institutions[0].country_code | SG |
| authorships[2].institutions[0].display_name | Singapore Management University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Junda He |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Singapore Management University |
| authorships[3].author.id | https://openalex.org/A5081036622 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-4367-7201 |
| authorships[3].author.display_name | David Lo |
| authorships[3].countries | SG |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I79891267 |
| authorships[3].affiliations[0].raw_affiliation_string | Singapore Management University |
| authorships[3].institutions[0].id | https://openalex.org/I79891267 |
| authorships[3].institutions[0].ror | https://ror.org/050qmg959 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I79891267 |
| authorships[3].institutions[0].country_code | SG |
| authorships[3].institutions[0].display_name | Singapore Management University |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | David Lo |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Singapore Management University |
| 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/2201.08698 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Natural attack for pre-trained models of code |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9993000030517578 |
| 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/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 130 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 37 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 47 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 39 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 7 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2201.08698 |
| 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/2201.08698 |
| 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/2201.08698 |
| primary_location.id | doi:10.1145/3510003.3510146 |
| primary_location.is_oa | False |
| primary_location.source.id | https://openalex.org/S4363608872 |
| primary_location.source.issn | |
| primary_location.source.type | conference |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the 44th International Conference on Software Engineering |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the 44th International Conference on Software Engineering |
| primary_location.landing_page_url | https://doi.org/10.1145/3510003.3510146 |
| publication_date | 2022-05-21 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W2887364112, https://openalex.org/W2964150020, https://openalex.org/W2742956140, https://openalex.org/W3199249334, https://openalex.org/W3025298766, https://openalex.org/W3098605233, https://openalex.org/W3090943961, https://openalex.org/W2962797416, https://openalex.org/W2327678559, https://openalex.org/W3011564318, https://openalex.org/W3101449015, https://openalex.org/W6600424091, https://openalex.org/W6602680078, https://openalex.org/W2056760934, https://openalex.org/W4206334468, https://openalex.org/W3167948855, https://openalex.org/W3131641316, https://openalex.org/W2962784628, https://openalex.org/W4225878270, https://openalex.org/W2065053490, https://openalex.org/W3108032709, https://openalex.org/W6606876336, https://openalex.org/W3014339000, https://openalex.org/W4286530321, https://openalex.org/W3109966548, https://openalex.org/W2997451752, https://openalex.org/W3096150021, https://openalex.org/W2811010710, https://openalex.org/W2804660315, https://openalex.org/W2996343955, https://openalex.org/W3155981360, https://openalex.org/W3105398568, https://openalex.org/W4293846201, https://openalex.org/W46679369, https://openalex.org/W2963499994, https://openalex.org/W2972135640, https://openalex.org/W2741705590, https://openalex.org/W2896457183, https://openalex.org/W4287265163, https://openalex.org/W4255315653, https://openalex.org/W1532325895, https://openalex.org/W3035882142, https://openalex.org/W2965373594, https://openalex.org/W1945616565, https://openalex.org/W4394638297, https://openalex.org/W2947477827, https://openalex.org/W3217001695, https://openalex.org/W4226216828, https://openalex.org/W2560674852, https://openalex.org/W2898734514, https://openalex.org/W3198685994, https://openalex.org/W2996851481, https://openalex.org/W4292779060, https://openalex.org/W4247880210, https://openalex.org/W3126675481, https://openalex.org/W2964301649, https://openalex.org/W3119507053, https://openalex.org/W2750779823, https://openalex.org/W3128630643, https://openalex.org/W3034549508, https://openalex.org/W4293159471, https://openalex.org/W3168895090, https://openalex.org/W2747329762 |
| referenced_works_count | 63 |
| abstract_inverted_index.a | 27, 47, 75 |
| abstract_inverted_index.In | 66 |
| abstract_inverted_index.On | 141, 165 |
| abstract_inverted_index.an | 210 |
| abstract_inverted_index.as | 63, 103 |
| abstract_inverted_index.at | 99 |
| abstract_inverted_index.be | 55 |
| abstract_inverted_index.by | 122, 129, 133, 186, 225 |
| abstract_inverted_index.et | 135 |
| abstract_inverted_index.in | 7 |
| abstract_inverted_index.of | 2, 37, 150, 201, 217 |
| abstract_inverted_index.on | 178, 190, 195 |
| abstract_inverted_index.to | 18, 25, 57, 62, 81 |
| abstract_inverted_index.we | 60, 69, 197 |
| abstract_inverted_index.Our | 110 |
| abstract_inverted_index.The | 182 |
| abstract_inverted_index.al. | 136 |
| abstract_inverted_index.and | 153, 162, 176, 188, 219, 227 |
| abstract_inverted_index.are | 16, 124 |
| abstract_inverted_index.but | 45 |
| abstract_inverted_index.can | 169 |
| abstract_inverted_index.our | 144, 167 |
| abstract_inverted_index.the | 94, 100, 105, 130, 138, 179, 191, 199, 202, 215 |
| abstract_inverted_index.two | 192 |
| abstract_inverted_index.code | 3, 38, 163 |
| abstract_inverted_index.from | 88 |
| abstract_inverted_index.have | 4 |
| abstract_inverted_index.make | 26, 82 |
| abstract_inverted_index.many | 8 |
| abstract_inverted_index.same | 101 |
| abstract_inverted_index.than | 126 |
| abstract_inverted_index.that | 20, 41, 77, 114, 118 |
| abstract_inverted_index.this | 67, 91 |
| abstract_inverted_index.time | 102 |
| abstract_inverted_index.user | 111 |
| abstract_inverted_index.with | 39 |
| abstract_inverted_index.work | 132 |
| abstract_inverted_index.7.96% | 175 |
| abstract_inverted_index.ALERT | 71, 123 |
| abstract_inverted_index.AwaRe | 73 |
| abstract_inverted_index.Zhang | 134 |
| abstract_inverted_index.above | 183 |
| abstract_inverted_index.clone | 160 |
| abstract_inverted_index.human | 115 |
| abstract_inverted_index.model | 23, 29 |
| abstract_inverted_index.paper | 92 |
| abstract_inverted_index.prior | 89 |
| abstract_inverted_index.rates | 149 |
| abstract_inverted_index.refer | 61 |
| abstract_inverted_index.study | 112 |
| abstract_inverted_index.these | 13 |
| abstract_inverted_index.those | 127 |
| abstract_inverted_index.three | 180 |
| abstract_inverted_index.value | 200 |
| abstract_inverted_index.which | 59 |
| abstract_inverted_index.works | 33 |
| abstract_inverted_index.14.07% | 187 |
| abstract_inverted_index.18.56% | 189 |
| abstract_inverted_index.35.78% | 154 |
| abstract_inverted_index.61.47% | 177 |
| abstract_inverted_index.87.59% | 226 |
| abstract_inverted_index.across | 155 |
| abstract_inverted_index.attack | 35, 147 |
| abstract_inverted_index.ignore | 46 |
| abstract_inverted_index.inputs | 24, 80 |
| abstract_inverted_index.mainly | 34 |
| abstract_inverted_index.models | 1, 15, 36, 84, 194, 208 |
| abstract_inverted_index.paper, | 68 |
| abstract_inverted_index.should | 54 |
| abstract_inverted_index.tasks. | 11, 181 |
| abstract_inverted_index.tasks: | 157 |
| abstract_inverted_index.victim | 28, 83, 207 |
| abstract_inverted_index.works, | 90 |
| abstract_inverted_index.27.79%, | 152 |
| abstract_inverted_index.53.62%, | 151 |
| abstract_inverted_index.76.95%, | 174 |
| abstract_inverted_index.92.32%, | 228 |
| abstract_inverted_index.Current | 32 |
| abstract_inverted_index.achieve | 170 |
| abstract_inverted_index.against | 221 |
| abstract_inverted_index.average | 171 |
| abstract_inverted_index.example | 51 |
| abstract_inverted_index.inputs. | 109 |
| abstract_inverted_index.natural | 56, 95 |
| abstract_inverted_index.perturb | 22 |
| abstract_inverted_index.produce | 30, 85 |
| abstract_inverted_index.program | 43 |
| abstract_inverted_index.propose | 70 |
| abstract_inverted_index.success | 6, 148, 172 |
| abstract_inverted_index.through | 209 |
| abstract_inverted_index.ATtack), | 74 |
| abstract_inverted_index.CodeBERT | 218 |
| abstract_inverted_index.However, | 12 |
| abstract_inverted_index.accuracy | 216 |
| abstract_inverted_index.achieved | 5 |
| abstract_inverted_index.approach | 145, 168 |
| abstract_inverted_index.consider | 117 |
| abstract_inverted_index.examples | 40, 98, 120, 205, 223 |
| abstract_inverted_index.original | 108 |
| abstract_inverted_index.powerful | 14 |
| abstract_inverted_index.slightly | 21 |
| abstract_inverted_index.CodeBERT, | 143 |
| abstract_inverted_index.Different | 87 |
| abstract_inverted_index.attacking | 142 |
| abstract_inverted_index.considers | 93 |
| abstract_inverted_index.detection | 161 |
| abstract_inverted_index.generated | 97, 121, 128, 203 |
| abstract_inverted_index.important | 9 |
| abstract_inverted_index.increased | 224 |
| abstract_inverted_index.procedure | 213 |
| abstract_inverted_index.rates\nof | 173 |
| abstract_inverted_index.semantics | 44 |
| abstract_inverted_index.preserving | 104 |
| abstract_inverted_index.to\nharden | 206 |
| abstract_inverted_index.transforms | 79 |
| abstract_inverted_index.vulnerable | 17 |
| abstract_inverted_index.Pre-trained | 0 |
| abstract_inverted_index.adversarial | 119, 204, 211 |
| abstract_inverted_index.fine-tuning | 212 |
| abstract_inverted_index.fundamental | 48 |
| abstract_inverted_index.generation: | 52 |
| abstract_inverted_index.naturalness | 64, 139 |
| abstract_inverted_index.operational | 106 |
| abstract_inverted_index.outperforms | 184 |
| abstract_inverted_index.pre-trained | 193 |
| abstract_inverted_index.prediction, | 159 |
| abstract_inverted_index.requirement | 49 |
| abstract_inverted_index.(nAturaLnEss | 72 |
| abstract_inverted_index.can\nachieve | 146 |
| abstract_inverted_index.demonstrates | 113 |
| abstract_inverted_index.investigated | 198 |
| abstract_inverted_index.requirement. | 140 |
| abstract_inverted_index.semantic\nof | 96, 107 |
| abstract_inverted_index.GraphCodeBERT | 220 |
| abstract_inverted_index.adversarially | 78 |
| abstract_inverted_index.more\nnatural | 125 |
| abstract_inverted_index.perturbations | 53 |
| abstract_inverted_index.that\nignores | 137 |
| abstract_inverted_index.the\nbaseline | 185 |
| abstract_inverted_index.vulnerability | 158 |
| abstract_inverted_index.GraphCodeBERT, | 166 |
| abstract_inverted_index.human\njudges, | 58 |
| abstract_inverted_index.requirement.\n | 65 |
| abstract_inverted_index.respectively.\n | 229 |
| abstract_inverted_index.wrong\noutputs. | 31, 86 |
| abstract_inverted_index.for\nadversarial | 50 |
| abstract_inverted_index.state-of-the-art | 131 |
| abstract_inverted_index.and\ndemonstrated | 214 |
| abstract_inverted_index.black-box\nattack | 76 |
| abstract_inverted_index.three\ndownstream | 156 |
| abstract_inverted_index.average.\nFinally, | 196 |
| abstract_inverted_index.adversarial\nattacks | 19 |
| abstract_inverted_index.preserve\noperational | 42 |
| abstract_inverted_index.software\nengineering | 10 |
| abstract_inverted_index.authorship\nattribution. | 164 |
| abstract_inverted_index.developers\nconsistently | 116 |
| abstract_inverted_index.ALERT-generated\nadversarial | 222 |
| cited_by_percentile_year.max | 100 |
| cited_by_percentile_year.min | 98 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.8500000238418579 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile.value | 0.99370475 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |