Backdoor Attacks on Image Classification Models in Deep Neural Networks Article Swipe
Quanxin ZHANG
,
Wencong MA
,
Yajie Wang
,
Yaoyuan Zhang
,
Zhiwei Shi
,
Yuanzhang Li
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1049/cje.2021.00.126
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1049/cje.2021.00.126
Deep neural network (DNN) is applied widely in many applications and achieves state-of-the-art performance. However, DNN lacks transparency and interpretability for users in structure. Attackers can use this feature to embed trojan horses in the DNN structure, such as inserting a backdoor into the DNN, so that DNN can learn both the normal main task and additional malicious tasks at the same time. Besides, DNN relies on data set for training. Attackers can tamper with training data to interfere with DNN training process, such as attaching a trigger on input data. Because of defects in DNN structure and data, the backdoor attack can be a serious threat to the security of DNN. The DNN attacked by backdoor performs well on benign inputs while it outputs an attacker-specified label on trigger attached inputs. Backdoor attack can be conducted in almost every stage of the machine learning pipeline. Although there are a few researches in the backdoor attack on image classification, a systematic review is still rare in this field. This paper is a comprehensive review of backdoor attacks. According to whether attackers have access to the training data, we divide various backdoor attacks into two types: poisoning-based attacks and non-poisoning-based attacks. We go through the details of each work in the timeline, discussing its contribution and deficiencies. We propose a detailed mathematical backdoor model to summary all kinds of backdoor attacks. In the end, we provide some insights about future studies.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1049/cje.2021.00.126
- https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cje.2021.00.126
- OA Status
- hybrid
- Cited By
- 25
- References
- 49
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3215147048
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3215147048Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1049/cje.2021.00.126Digital Object Identifier
- Title
-
Backdoor Attacks on Image Classification Models in Deep Neural NetworksWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-03-01Full publication date if available
- Authors
-
Quanxin ZHANG, Wencong MA, Yajie Wang, Yaoyuan Zhang, Zhiwei Shi, Yuanzhang LiList of authors in order
- Landing page
-
https://doi.org/10.1049/cje.2021.00.126Publisher landing page
- PDF URL
-
https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cje.2021.00.126Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cje.2021.00.126Direct OA link when available
- Concepts
-
Backdoor, Computer science, Interpretability, Artificial intelligence, Artificial neural network, Machine learning, Feature (linguistics), Deep learning, Computer security, Philosophy, LinguisticsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
25Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 4, 2024: 9, 2023: 12Per-year citation counts (last 5 years)
- References (count)
-
49Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3215147048 |
|---|---|
| doi | https://doi.org/10.1049/cje.2021.00.126 |
| ids.doi | https://doi.org/10.1049/cje.2021.00.126 |
| ids.mag | 3215147048 |
| ids.openalex | https://openalex.org/W3215147048 |
| fwci | 4.89497051 |
| type | article |
| title | Backdoor Attacks on Image Classification Models in Deep Neural Networks |
| awards[0].id | https://openalex.org/G7580715247 |
| awards[0].funder_id | https://openalex.org/F4320321001 |
| awards[0].display_name | |
| awards[0].funder_award_id | 61876019 |
| awards[0].funder_display_name | National Natural Science Foundation of China |
| biblio.issue | 2 |
| biblio.volume | 31 |
| biblio.last_page | 212 |
| biblio.first_page | 199 |
| 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 | 0.9998999834060669 |
| 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/T11241 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9825000166893005 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1711 |
| topics[1].subfield.display_name | Signal Processing |
| topics[1].display_name | Advanced Malware Detection Techniques |
| topics[2].id | https://openalex.org/T11512 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9373999834060669 |
| 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 | Anomaly Detection Techniques and Applications |
| funders[0].id | https://openalex.org/F4320321001 |
| funders[0].ror | https://ror.org/01h0zpd94 |
| funders[0].display_name | National Natural Science Foundation of China |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2781045450 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9986969232559204 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q254569 |
| concepts[0].display_name | Backdoor |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7626913785934448 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2781067378 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6614963412284851 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17027399 |
| concepts[2].display_name | Interpretability |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5735393762588501 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C50644808 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5316023826599121 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[4].display_name | Artificial neural network |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.44305017590522766 |
| 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 | 0.43429285287857056 |
| 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 | 0.4130558371543884 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[7].display_name | Deep learning |
| concepts[8].id | https://openalex.org/C38652104 |
| concepts[8].level | 1 |
| concepts[8].score | 0.3081623911857605 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[8].display_name | Computer security |
| concepts[9].id | https://openalex.org/C138885662 |
| concepts[9].level | 0 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[9].display_name | Philosophy |
| concepts[10].id | https://openalex.org/C41895202 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[10].display_name | Linguistics |
| keywords[0].id | https://openalex.org/keywords/backdoor |
| keywords[0].score | 0.9986969232559204 |
| keywords[0].display_name | Backdoor |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7626913785934448 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/interpretability |
| keywords[2].score | 0.6614963412284851 |
| keywords[2].display_name | Interpretability |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5735393762588501 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[4].score | 0.5316023826599121 |
| keywords[4].display_name | Artificial neural network |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.44305017590522766 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/feature |
| keywords[6].score | 0.43429285287857056 |
| keywords[6].display_name | Feature (linguistics) |
| keywords[7].id | https://openalex.org/keywords/deep-learning |
| keywords[7].score | 0.4130558371543884 |
| keywords[7].display_name | Deep learning |
| keywords[8].id | https://openalex.org/keywords/computer-security |
| keywords[8].score | 0.3081623911857605 |
| keywords[8].display_name | Computer security |
| language | en |
| locations[0].id | doi:10.1049/cje.2021.00.126 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S144330684 |
| locations[0].source.issn | 1022-4653, 2075-5597 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 1022-4653 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Chinese Journal of Electronics |
| locations[0].source.host_organization | https://openalex.org/P4310311714 |
| locations[0].source.host_organization_name | Institution of Engineering and Technology |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310311714 |
| locations[0].source.host_organization_lineage_names | Institution of Engineering and Technology |
| locations[0].license | cc-by-nc-sa |
| locations[0].pdf_url | https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cje.2021.00.126 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-sa |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Chinese Journal of Electronics |
| locations[0].landing_page_url | https://doi.org/10.1049/cje.2021.00.126 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5046779128 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Quanxin ZHANG |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I125839683 |
| authorships[0].affiliations[0].raw_affiliation_string | Beijing Institute of Technology, Beijing, 100036 China |
| authorships[0].institutions[0].id | https://openalex.org/I125839683 |
| authorships[0].institutions[0].ror | https://ror.org/01skt4w74 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I125839683, https://openalex.org/I890469752 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Beijing Institute of Technology |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Quanxin ZHANG |
| authorships[0].is_corresponding | True |
| authorships[0].raw_affiliation_strings | Beijing Institute of Technology, Beijing, 100036 China |
| authorships[1].author.id | https://openalex.org/A5102138147 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Wencong MA |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I125839683 |
| authorships[1].affiliations[0].raw_affiliation_string | Beijing Institute of Technology, Beijing, 100036 China |
| authorships[1].institutions[0].id | https://openalex.org/I125839683 |
| authorships[1].institutions[0].ror | https://ror.org/01skt4w74 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I125839683, https://openalex.org/I890469752 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Beijing Institute of Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wencong MA |
| authorships[1].is_corresponding | True |
| authorships[1].raw_affiliation_strings | Beijing Institute of Technology, Beijing, 100036 China |
| authorships[2].author.id | https://openalex.org/A5100455413 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-0962-4464 |
| authorships[2].author.display_name | Yajie Wang |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I125839683 |
| authorships[2].affiliations[0].raw_affiliation_string | Beijing Institute of Technology, Beijing, 100036 China |
| authorships[2].institutions[0].id | https://openalex.org/I125839683 |
| authorships[2].institutions[0].ror | https://ror.org/01skt4w74 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I125839683, https://openalex.org/I890469752 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Beijing Institute of Technology |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Yajie WANG |
| authorships[2].is_corresponding | True |
| authorships[2].raw_affiliation_strings | Beijing Institute of Technology, Beijing, 100036 China |
| authorships[3].author.id | https://openalex.org/A5047829642 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-3732-0115 |
| authorships[3].author.display_name | Yaoyuan Zhang |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I125839683 |
| authorships[3].affiliations[0].raw_affiliation_string | Beijing Institute of Technology, Beijing, 100036 China |
| authorships[3].institutions[0].id | https://openalex.org/I125839683 |
| authorships[3].institutions[0].ror | https://ror.org/01skt4w74 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I125839683, https://openalex.org/I890469752 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Beijing Institute of Technology |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yaoyuan ZHANG |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Beijing Institute of Technology, Beijing, 100036 China |
| authorships[4].author.id | https://openalex.org/A5101815702 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-9111-5342 |
| authorships[4].author.display_name | Zhiwei Shi |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I4210160629 |
| authorships[4].affiliations[0].raw_affiliation_string | China Information Technology Security Evaluation Center, Beijing, 100085 China |
| authorships[4].institutions[0].id | https://openalex.org/I4210160629 |
| authorships[4].institutions[0].ror | https://ror.org/053cexp66 |
| authorships[4].institutions[0].type | government |
| authorships[4].institutions[0].lineage | https://openalex.org/I4210160629 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | China Information Technology Security Evaluation Center |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zhiwei SHI |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | China Information Technology Security Evaluation Center, Beijing, 100085 China |
| authorships[5].author.id | https://openalex.org/A5026287089 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-1931-366X |
| authorships[5].author.display_name | Yuanzhang Li |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I125839683 |
| authorships[5].affiliations[0].raw_affiliation_string | Beijing Institute of Technology, Beijing, 100036 China |
| authorships[5].institutions[0].id | https://openalex.org/I125839683 |
| authorships[5].institutions[0].ror | https://ror.org/01skt4w74 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I125839683, https://openalex.org/I890469752 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | Beijing Institute of Technology |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Yuanzhang LI |
| authorships[5].is_corresponding | True |
| authorships[5].raw_affiliation_strings | Beijing Institute of Technology, Beijing, 100036 China |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cje.2021.00.126 |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Backdoor Attacks on Image Classification Models in Deep Neural Networks |
| has_fulltext | False |
| 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 | 0.9998999834060669 |
| 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/W4320031223, https://openalex.org/W4200629851, https://openalex.org/W4281902577, https://openalex.org/W4309417370, https://openalex.org/W4292107232, https://openalex.org/W3009072493, https://openalex.org/W4386080799, https://openalex.org/W3140988292, https://openalex.org/W4317672133, https://openalex.org/W4386185023 |
| cited_by_count | 25 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 4 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 9 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 12 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1049/cje.2021.00.126 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S144330684 |
| best_oa_location.source.issn | 1022-4653, 2075-5597 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 1022-4653 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Chinese Journal of Electronics |
| best_oa_location.source.host_organization | https://openalex.org/P4310311714 |
| best_oa_location.source.host_organization_name | Institution of Engineering and Technology |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310311714 |
| best_oa_location.source.host_organization_lineage_names | Institution of Engineering and Technology |
| best_oa_location.license | cc-by-nc-sa |
| best_oa_location.pdf_url | https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cje.2021.00.126 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-sa |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Chinese Journal of Electronics |
| best_oa_location.landing_page_url | https://doi.org/10.1049/cje.2021.00.126 |
| primary_location.id | doi:10.1049/cje.2021.00.126 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S144330684 |
| primary_location.source.issn | 1022-4653, 2075-5597 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 1022-4653 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Chinese Journal of Electronics |
| primary_location.source.host_organization | https://openalex.org/P4310311714 |
| primary_location.source.host_organization_name | Institution of Engineering and Technology |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310311714 |
| primary_location.source.host_organization_lineage_names | Institution of Engineering and Technology |
| primary_location.license | cc-by-nc-sa |
| primary_location.pdf_url | https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cje.2021.00.126 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-sa |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Chinese Journal of Electronics |
| primary_location.landing_page_url | https://doi.org/10.1049/cje.2021.00.126 |
| publication_date | 2022-03-01 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W2912581782, https://openalex.org/W2903650079, https://openalex.org/W2962883549, https://openalex.org/W2678047256, https://openalex.org/W2603766943, https://openalex.org/W2607219512, https://openalex.org/W2157116240, https://openalex.org/W2311417940, https://openalex.org/W2973217491, https://openalex.org/W3204619801, https://openalex.org/W3035367371, https://openalex.org/W2917251332, https://openalex.org/W2774423163, https://openalex.org/W2807363941, https://openalex.org/W3043789969, https://openalex.org/W4206230075, https://openalex.org/W3130788031, https://openalex.org/W6775678023, https://openalex.org/W3012113073, https://openalex.org/W2900018096, https://openalex.org/W3010216907, https://openalex.org/W3096831136, https://openalex.org/W3108700588, https://openalex.org/W2990270730, https://openalex.org/W2791218785, https://openalex.org/W2985913519, https://openalex.org/W3022042319, https://openalex.org/W2996800219, https://openalex.org/W3007930164, https://openalex.org/W2230451675, https://openalex.org/W2161998562, https://openalex.org/W2142145056, https://openalex.org/W3086120435, https://openalex.org/W1849277567, https://openalex.org/W4253050311, https://openalex.org/W4301409532, https://openalex.org/W4233210494, https://openalex.org/W4376585873, https://openalex.org/W4212949137, https://openalex.org/W3175215793, https://openalex.org/W3083185154, https://openalex.org/W1968389182, https://openalex.org/W592027770, https://openalex.org/W2963265635, https://openalex.org/W3102720581, https://openalex.org/W4212774754, https://openalex.org/W4353004773, https://openalex.org/W2600756564, https://openalex.org/W3015678314 |
| referenced_works_count | 49 |
| abstract_inverted_index.a | 40, 86, 104, 149, 159, 171, 218 |
| abstract_inverted_index.In | 230 |
| abstract_inverted_index.We | 200, 216 |
| abstract_inverted_index.an | 125 |
| abstract_inverted_index.as | 38, 84 |
| abstract_inverted_index.at | 59 |
| abstract_inverted_index.be | 103, 135 |
| abstract_inverted_index.by | 115 |
| abstract_inverted_index.go | 201 |
| abstract_inverted_index.in | 7, 22, 33, 94, 137, 152, 165, 208 |
| abstract_inverted_index.is | 4, 162, 170 |
| abstract_inverted_index.it | 123 |
| abstract_inverted_index.of | 92, 110, 141, 174, 205, 227 |
| abstract_inverted_index.on | 66, 88, 119, 128, 156 |
| abstract_inverted_index.so | 45 |
| abstract_inverted_index.to | 29, 77, 107, 178, 183, 223 |
| abstract_inverted_index.we | 187, 233 |
| abstract_inverted_index.DNN | 15, 35, 47, 64, 80, 95, 113 |
| abstract_inverted_index.The | 112 |
| abstract_inverted_index.all | 225 |
| abstract_inverted_index.and | 10, 18, 55, 97, 197, 214 |
| abstract_inverted_index.are | 148 |
| abstract_inverted_index.can | 25, 48, 72, 102, 134 |
| abstract_inverted_index.few | 150 |
| abstract_inverted_index.for | 20, 69 |
| abstract_inverted_index.its | 212 |
| abstract_inverted_index.set | 68 |
| abstract_inverted_index.the | 34, 43, 51, 60, 99, 108, 142, 153, 184, 203, 209, 231 |
| abstract_inverted_index.two | 193 |
| abstract_inverted_index.use | 26 |
| abstract_inverted_index.DNN, | 44 |
| abstract_inverted_index.DNN. | 111 |
| abstract_inverted_index.Deep | 0 |
| abstract_inverted_index.This | 168 |
| abstract_inverted_index.both | 50 |
| abstract_inverted_index.data | 67, 76 |
| abstract_inverted_index.each | 206 |
| abstract_inverted_index.end, | 232 |
| abstract_inverted_index.have | 181 |
| abstract_inverted_index.into | 42, 192 |
| abstract_inverted_index.main | 53 |
| abstract_inverted_index.many | 8 |
| abstract_inverted_index.rare | 164 |
| abstract_inverted_index.same | 61 |
| abstract_inverted_index.some | 235 |
| abstract_inverted_index.such | 37, 83 |
| abstract_inverted_index.task | 54 |
| abstract_inverted_index.that | 46 |
| abstract_inverted_index.this | 27, 166 |
| abstract_inverted_index.well | 118 |
| abstract_inverted_index.with | 74, 79 |
| abstract_inverted_index.work | 207 |
| abstract_inverted_index.(DNN) | 3 |
| abstract_inverted_index.about | 237 |
| abstract_inverted_index.data, | 98, 186 |
| abstract_inverted_index.data. | 90 |
| abstract_inverted_index.embed | 30 |
| abstract_inverted_index.every | 139 |
| abstract_inverted_index.image | 157 |
| abstract_inverted_index.input | 89 |
| abstract_inverted_index.kinds | 226 |
| abstract_inverted_index.label | 127 |
| abstract_inverted_index.lacks | 16 |
| abstract_inverted_index.learn | 49 |
| abstract_inverted_index.model | 222 |
| abstract_inverted_index.paper | 169 |
| abstract_inverted_index.stage | 140 |
| abstract_inverted_index.still | 163 |
| abstract_inverted_index.tasks | 58 |
| abstract_inverted_index.there | 147 |
| abstract_inverted_index.time. | 62 |
| abstract_inverted_index.users | 21 |
| abstract_inverted_index.while | 122 |
| abstract_inverted_index.access | 182 |
| abstract_inverted_index.almost | 138 |
| abstract_inverted_index.attack | 101, 133, 155 |
| abstract_inverted_index.benign | 120 |
| abstract_inverted_index.divide | 188 |
| abstract_inverted_index.field. | 167 |
| abstract_inverted_index.future | 238 |
| abstract_inverted_index.horses | 32 |
| abstract_inverted_index.inputs | 121 |
| abstract_inverted_index.neural | 1 |
| abstract_inverted_index.normal | 52 |
| abstract_inverted_index.relies | 65 |
| abstract_inverted_index.review | 161, 173 |
| abstract_inverted_index.tamper | 73 |
| abstract_inverted_index.threat | 106 |
| abstract_inverted_index.trojan | 31 |
| abstract_inverted_index.types: | 194 |
| abstract_inverted_index.widely | 6 |
| abstract_inverted_index.Because | 91 |
| abstract_inverted_index.applied | 5 |
| abstract_inverted_index.attacks | 191, 196 |
| abstract_inverted_index.defects | 93 |
| abstract_inverted_index.details | 204 |
| abstract_inverted_index.feature | 28 |
| abstract_inverted_index.inputs. | 131 |
| abstract_inverted_index.machine | 143 |
| abstract_inverted_index.network | 2 |
| abstract_inverted_index.outputs | 124 |
| abstract_inverted_index.propose | 217 |
| abstract_inverted_index.provide | 234 |
| abstract_inverted_index.serious | 105 |
| abstract_inverted_index.summary | 224 |
| abstract_inverted_index.through | 202 |
| abstract_inverted_index.trigger | 87, 129 |
| abstract_inverted_index.various | 189 |
| abstract_inverted_index.whether | 179 |
| abstract_inverted_index.Although | 146 |
| abstract_inverted_index.Backdoor | 132 |
| abstract_inverted_index.Besides, | 63 |
| abstract_inverted_index.However, | 14 |
| abstract_inverted_index.achieves | 11 |
| abstract_inverted_index.attached | 130 |
| abstract_inverted_index.attacked | 114 |
| abstract_inverted_index.attacks. | 176, 199, 229 |
| abstract_inverted_index.backdoor | 41, 100, 116, 154, 175, 190, 221, 228 |
| abstract_inverted_index.detailed | 219 |
| abstract_inverted_index.insights | 236 |
| abstract_inverted_index.learning | 144 |
| abstract_inverted_index.performs | 117 |
| abstract_inverted_index.process, | 82 |
| abstract_inverted_index.security | 109 |
| abstract_inverted_index.studies. | 239 |
| abstract_inverted_index.training | 75, 81, 185 |
| abstract_inverted_index.According | 177 |
| abstract_inverted_index.Attackers | 24, 71 |
| abstract_inverted_index.attaching | 85 |
| abstract_inverted_index.attackers | 180 |
| abstract_inverted_index.conducted | 136 |
| abstract_inverted_index.inserting | 39 |
| abstract_inverted_index.interfere | 78 |
| abstract_inverted_index.malicious | 57 |
| abstract_inverted_index.pipeline. | 145 |
| abstract_inverted_index.structure | 96 |
| abstract_inverted_index.timeline, | 210 |
| abstract_inverted_index.training. | 70 |
| abstract_inverted_index.additional | 56 |
| abstract_inverted_index.discussing | 211 |
| abstract_inverted_index.researches | 151 |
| abstract_inverted_index.structure, | 36 |
| abstract_inverted_index.structure. | 23 |
| abstract_inverted_index.systematic | 160 |
| abstract_inverted_index.applications | 9 |
| abstract_inverted_index.contribution | 213 |
| abstract_inverted_index.mathematical | 220 |
| abstract_inverted_index.performance. | 13 |
| abstract_inverted_index.transparency | 17 |
| abstract_inverted_index.comprehensive | 172 |
| abstract_inverted_index.deficiencies. | 215 |
| abstract_inverted_index.classification, | 158 |
| abstract_inverted_index.poisoning-based | 195 |
| abstract_inverted_index.interpretability | 19 |
| abstract_inverted_index.state-of-the-art | 12 |
| abstract_inverted_index.attacker-specified | 126 |
| abstract_inverted_index.non-poisoning-based | 198 |
| cited_by_percentile_year.max | 99 |
| cited_by_percentile_year.min | 97 |
| corresponding_author_ids | https://openalex.org/A5026287089, https://openalex.org/A5102138147, https://openalex.org/A5100455413, https://openalex.org/A5046779128 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 6 |
| corresponding_institution_ids | https://openalex.org/I125839683 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.5600000023841858 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile.value | 0.93624453 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |