QuanDA: GPU Accelerated Quantitative Deep Neural Network Analysis Article Swipe
Mahum Naseer
,
Osman Hasan
,
Muhammad Shafique
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1145/3611671
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1145/3611671
Over the past years, numerous studies demonstrated the vulnerability of deep neural networks (DNNs) to make correct classifications in the presence of small noise. This motivated the formal analysis of DNNs to ensure that they delineate acceptable behavior. However, in the case that the DNN’s behavior is unacceptable for the desired application, these qualitative approaches are ill equipped to determine the precise degree to which the DNN behaves unacceptably. We propose a novel quantitative DNN analysis framework, QuanDA, which not only checks whether the DNN delineates certain behavior but also provides the estimated probability of the DNN to delineate this particular behavior. Unlike the (few) available quantitative DNN analysis frameworks, QuanDA does not use any implicit assumptions on the probability distribution of the hidden nodes, which enables the framework to propagate close to real probability distributions of the hidden node values to each proceeding DNN layer. Furthermore, our framework leverages CUDA to parallelize the analysis, enabling high-speed GPU implementation for fast analysis. The applicability of the framework is demonstrated using the ACAS Xu benchmark, to provide reachability probability estimates for all network nodes. This paper also provides potential applications of QuanDA for the analysis of DNN safety properties.
Related Topics
Concepts
Computer science
Benchmark (surveying)
Reachability
CUDA
Deep neural networks
Node (physics)
Artificial neural network
Probability distribution
Noise (video)
Artificial intelligence
Machine learning
Theoretical computer science
Parallel computing
Structural engineering
Statistics
Image (mathematics)
Mathematics
Geography
Geodesy
Engineering
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1145/3611671
- https://dl.acm.org/doi/pdf/10.1145/3611671
- OA Status
- hybrid
- References
- 32
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4385456266
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4385456266Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1145/3611671Digital Object Identifier
- Title
-
QuanDA: GPU Accelerated Quantitative Deep Neural Network AnalysisWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-08-01Full publication date if available
- Authors
-
Mahum Naseer, Osman Hasan, Muhammad ShafiqueList of authors in order
- Landing page
-
https://doi.org/10.1145/3611671Publisher landing page
- PDF URL
-
https://dl.acm.org/doi/pdf/10.1145/3611671Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://dl.acm.org/doi/pdf/10.1145/3611671Direct OA link when available
- Concepts
-
Computer science, Benchmark (surveying), Reachability, CUDA, Deep neural networks, Node (physics), Artificial neural network, Probability distribution, Noise (video), Artificial intelligence, Machine learning, Theoretical computer science, Parallel computing, Structural engineering, Statistics, Image (mathematics), Mathematics, Geography, Geodesy, EngineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
32Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4385456266 |
|---|---|
| doi | https://doi.org/10.1145/3611671 |
| ids.doi | https://doi.org/10.1145/3611671 |
| ids.openalex | https://openalex.org/W4385456266 |
| fwci | 0.0 |
| type | article |
| title | QuanDA: GPU Accelerated Quantitative Deep Neural Network Analysis |
| awards[0].id | https://openalex.org/G5357824321 |
| awards[0].funder_id | https://openalex.org/F4320327207 |
| awards[0].display_name | |
| awards[0].funder_award_id | H2020-ECSEL-2019-IA-876190 |
| awards[0].funder_display_name | Electronic Components and Systems for European Leadership |
| biblio.issue | 6 |
| biblio.volume | 28 |
| biblio.last_page | 21 |
| biblio.first_page | 1 |
| 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 | 1.0 |
| 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/T10036 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9914000034332275 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Neural Network Applications |
| topics[2].id | https://openalex.org/T11307 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.979200005531311 |
| 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 | Domain Adaptation and Few-Shot Learning |
| funders[0].id | https://openalex.org/F4320327207 |
| funders[0].ror | |
| funders[0].display_name | Electronic Components and Systems for European Leadership |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.9035113453865051 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C185798385 |
| concepts[1].level | 2 |
| concepts[1].score | 0.682333767414093 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1161707 |
| concepts[1].display_name | Benchmark (surveying) |
| concepts[2].id | https://openalex.org/C136643341 |
| concepts[2].level | 2 |
| concepts[2].score | 0.63640296459198 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1361526 |
| concepts[2].display_name | Reachability |
| concepts[3].id | https://openalex.org/C2778119891 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6139180660247803 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q477690 |
| concepts[3].display_name | CUDA |
| concepts[4].id | https://openalex.org/C2984842247 |
| concepts[4].level | 3 |
| concepts[4].score | 0.556413471698761 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[4].display_name | Deep neural networks |
| concepts[5].id | https://openalex.org/C62611344 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5536572933197021 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1062658 |
| concepts[5].display_name | Node (physics) |
| concepts[6].id | https://openalex.org/C50644808 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5101938247680664 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[6].display_name | Artificial neural network |
| concepts[7].id | https://openalex.org/C149441793 |
| concepts[7].level | 2 |
| concepts[7].score | 0.49877429008483887 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q200726 |
| concepts[7].display_name | Probability distribution |
| concepts[8].id | https://openalex.org/C99498987 |
| concepts[8].level | 3 |
| concepts[8].score | 0.4575686752796173 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2210247 |
| concepts[8].display_name | Noise (video) |
| concepts[9].id | https://openalex.org/C154945302 |
| concepts[9].level | 1 |
| concepts[9].score | 0.4225788712501526 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[9].display_name | Artificial intelligence |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3408343493938446 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C80444323 |
| concepts[11].level | 1 |
| concepts[11].score | 0.308318555355072 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[11].display_name | Theoretical computer science |
| concepts[12].id | https://openalex.org/C173608175 |
| concepts[12].level | 1 |
| concepts[12].score | 0.21358534693717957 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q232661 |
| concepts[12].display_name | Parallel computing |
| concepts[13].id | https://openalex.org/C66938386 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q633538 |
| concepts[13].display_name | Structural engineering |
| concepts[14].id | https://openalex.org/C105795698 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[14].display_name | Statistics |
| concepts[15].id | https://openalex.org/C115961682 |
| concepts[15].level | 2 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[15].display_name | Image (mathematics) |
| concepts[16].id | https://openalex.org/C33923547 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[16].display_name | Mathematics |
| 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 |
| concepts[18].id | https://openalex.org/C13280743 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q131089 |
| concepts[18].display_name | Geodesy |
| concepts[19].id | https://openalex.org/C127413603 |
| concepts[19].level | 0 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[19].display_name | Engineering |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.9035113453865051 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/benchmark |
| keywords[1].score | 0.682333767414093 |
| keywords[1].display_name | Benchmark (surveying) |
| keywords[2].id | https://openalex.org/keywords/reachability |
| keywords[2].score | 0.63640296459198 |
| keywords[2].display_name | Reachability |
| keywords[3].id | https://openalex.org/keywords/cuda |
| keywords[3].score | 0.6139180660247803 |
| keywords[3].display_name | CUDA |
| keywords[4].id | https://openalex.org/keywords/deep-neural-networks |
| keywords[4].score | 0.556413471698761 |
| keywords[4].display_name | Deep neural networks |
| keywords[5].id | https://openalex.org/keywords/node |
| keywords[5].score | 0.5536572933197021 |
| keywords[5].display_name | Node (physics) |
| keywords[6].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[6].score | 0.5101938247680664 |
| keywords[6].display_name | Artificial neural network |
| keywords[7].id | https://openalex.org/keywords/probability-distribution |
| keywords[7].score | 0.49877429008483887 |
| keywords[7].display_name | Probability distribution |
| keywords[8].id | https://openalex.org/keywords/noise |
| keywords[8].score | 0.4575686752796173 |
| keywords[8].display_name | Noise (video) |
| keywords[9].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[9].score | 0.4225788712501526 |
| keywords[9].display_name | Artificial intelligence |
| keywords[10].id | https://openalex.org/keywords/machine-learning |
| keywords[10].score | 0.3408343493938446 |
| keywords[10].display_name | Machine learning |
| keywords[11].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[11].score | 0.308318555355072 |
| keywords[11].display_name | Theoretical computer science |
| keywords[12].id | https://openalex.org/keywords/parallel-computing |
| keywords[12].score | 0.21358534693717957 |
| keywords[12].display_name | Parallel computing |
| language | en |
| locations[0].id | doi:10.1145/3611671 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S105046310 |
| locations[0].source.issn | 1084-4309, 1557-7309 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 1084-4309 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | ACM Transactions on Design Automation of Electronic Systems |
| locations[0].source.host_organization | https://openalex.org/P4310319798 |
| locations[0].source.host_organization_name | Association for Computing Machinery |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319798 |
| locations[0].source.host_organization_lineage_names | Association for Computing Machinery |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://dl.acm.org/doi/pdf/10.1145/3611671 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-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 | ACM Transactions on Design Automation of Electronic Systems |
| locations[0].landing_page_url | https://doi.org/10.1145/3611671 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5032460892 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-3096-9536 |
| authorships[0].author.display_name | Mahum Naseer |
| authorships[0].countries | AT |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I145847075 |
| authorships[0].affiliations[0].raw_affiliation_string | Institute of Computer Engineering, Vienna University of Technology, Austria |
| authorships[0].institutions[0].id | https://openalex.org/I145847075 |
| authorships[0].institutions[0].ror | https://ror.org/04d836q62 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I145847075 |
| authorships[0].institutions[0].country_code | AT |
| authorships[0].institutions[0].display_name | TU Wien |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Mahum Naseer |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Institute of Computer Engineering, Vienna University of Technology, Austria |
| authorships[1].author.id | https://openalex.org/A5066768973 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2562-2669 |
| authorships[1].author.display_name | Osman Hasan |
| authorships[1].countries | PK |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I929597975 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Electrical Engineering & Computer Science (SEECS), National University of Sciences & Technology (NUST), Pakistan |
| authorships[1].institutions[0].id | https://openalex.org/I929597975 |
| authorships[1].institutions[0].ror | https://ror.org/03w2j5y17 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I929597975 |
| authorships[1].institutions[0].country_code | PK |
| authorships[1].institutions[0].display_name | National University of Sciences and Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Osman Hasan |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Electrical Engineering & Computer Science (SEECS), National University of Sciences & Technology (NUST), Pakistan |
| authorships[2].author.id | https://openalex.org/A5005190949 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2607-8135 |
| authorships[2].author.display_name | Muhammad Shafique |
| authorships[2].countries | AE |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I120250893 |
| authorships[2].affiliations[0].raw_affiliation_string | Division of Engineering, New York University Abu Dhabi (NYUAD), United Arab Emirates |
| authorships[2].institutions[0].id | https://openalex.org/I120250893 |
| authorships[2].institutions[0].ror | https://ror.org/00e5k0821 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I120250893, https://openalex.org/I57206974 |
| authorships[2].institutions[0].country_code | AE |
| authorships[2].institutions[0].display_name | New York University Abu Dhabi |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Muhammad Shafique |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Division of Engineering, New York University Abu Dhabi (NYUAD), United Arab Emirates |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://dl.acm.org/doi/pdf/10.1145/3611671 |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | QuanDA: GPU Accelerated Quantitative Deep Neural Network Analysis |
| 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 | 1.0 |
| 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/W2136512912, https://openalex.org/W2127267268, https://openalex.org/W2156446763, https://openalex.org/W2067910792, https://openalex.org/W2150194458, https://openalex.org/W2143461633, https://openalex.org/W2889071233, https://openalex.org/W4321471459, https://openalex.org/W4221156924, https://openalex.org/W2380814829 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1145/3611671 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S105046310 |
| best_oa_location.source.issn | 1084-4309, 1557-7309 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 1084-4309 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | ACM Transactions on Design Automation of Electronic Systems |
| best_oa_location.source.host_organization | https://openalex.org/P4310319798 |
| best_oa_location.source.host_organization_name | Association for Computing Machinery |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310319798 |
| best_oa_location.source.host_organization_lineage_names | Association for Computing Machinery |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3611671 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-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 | ACM Transactions on Design Automation of Electronic Systems |
| best_oa_location.landing_page_url | https://doi.org/10.1145/3611671 |
| primary_location.id | doi:10.1145/3611671 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S105046310 |
| primary_location.source.issn | 1084-4309, 1557-7309 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 1084-4309 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | ACM Transactions on Design Automation of Electronic Systems |
| primary_location.source.host_organization | https://openalex.org/P4310319798 |
| primary_location.source.host_organization_name | Association for Computing Machinery |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319798 |
| primary_location.source.host_organization_lineage_names | Association for Computing Machinery |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3611671 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-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 | ACM Transactions on Design Automation of Electronic Systems |
| primary_location.landing_page_url | https://doi.org/10.1145/3611671 |
| publication_date | 2023-08-01 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W2325429064, https://openalex.org/W1498855283, https://openalex.org/W2972713160, https://openalex.org/W2788645721, https://openalex.org/W3102961483, https://openalex.org/W2791251367, https://openalex.org/W2963054787, https://openalex.org/W2905810301, https://openalex.org/W2041091076, https://openalex.org/W2103012681, https://openalex.org/W2543296129, https://openalex.org/W2594877703, https://openalex.org/W2957311447, https://openalex.org/W3101584909, https://openalex.org/W4206840646, https://openalex.org/W2616028256, https://openalex.org/W2004252880, https://openalex.org/W2897317743, https://openalex.org/W6755797642, https://openalex.org/W3216578534, https://openalex.org/W2604319603, https://openalex.org/W6637162671, https://openalex.org/W3198519141, https://openalex.org/W3196252426, https://openalex.org/W4297814571, https://openalex.org/W2900153411, https://openalex.org/W4251795452, https://openalex.org/W2559655401, https://openalex.org/W3012981624, https://openalex.org/W2153110463, https://openalex.org/W2525579820, https://openalex.org/W4212774754 |
| referenced_works_count | 32 |
| abstract_inverted_index.a | 71 |
| abstract_inverted_index.We | 69 |
| abstract_inverted_index.Xu | 172 |
| abstract_inverted_index.in | 18, 39 |
| abstract_inverted_index.is | 46, 167 |
| abstract_inverted_index.of | 9, 21, 29, 94, 121, 136, 164, 189, 194 |
| abstract_inverted_index.on | 117 |
| abstract_inverted_index.to | 14, 31, 58, 63, 97, 129, 132, 141, 151, 174 |
| abstract_inverted_index.DNN | 66, 74, 84, 96, 107, 144, 195 |
| abstract_inverted_index.GPU | 157 |
| abstract_inverted_index.The | 162 |
| abstract_inverted_index.all | 180 |
| abstract_inverted_index.any | 114 |
| abstract_inverted_index.are | 55 |
| abstract_inverted_index.but | 88 |
| abstract_inverted_index.for | 48, 159, 179, 191 |
| abstract_inverted_index.ill | 56 |
| abstract_inverted_index.not | 79, 112 |
| abstract_inverted_index.our | 147 |
| abstract_inverted_index.the | 1, 7, 19, 26, 40, 43, 49, 60, 65, 83, 91, 95, 103, 118, 122, 127, 137, 153, 165, 170, 192 |
| abstract_inverted_index.use | 113 |
| abstract_inverted_index.ACAS | 171 |
| abstract_inverted_index.CUDA | 150 |
| abstract_inverted_index.DNNs | 30 |
| abstract_inverted_index.Over | 0 |
| abstract_inverted_index.This | 24, 183 |
| abstract_inverted_index.also | 89, 185 |
| abstract_inverted_index.case | 41 |
| abstract_inverted_index.deep | 10 |
| abstract_inverted_index.does | 111 |
| abstract_inverted_index.each | 142 |
| abstract_inverted_index.fast | 160 |
| abstract_inverted_index.make | 15 |
| abstract_inverted_index.node | 139 |
| abstract_inverted_index.only | 80 |
| abstract_inverted_index.past | 2 |
| abstract_inverted_index.real | 133 |
| abstract_inverted_index.that | 33, 42 |
| abstract_inverted_index.they | 34 |
| abstract_inverted_index.this | 99 |
| abstract_inverted_index.(few) | 104 |
| abstract_inverted_index.close | 131 |
| abstract_inverted_index.novel | 72 |
| abstract_inverted_index.paper | 184 |
| abstract_inverted_index.small | 22 |
| abstract_inverted_index.these | 52 |
| abstract_inverted_index.using | 169 |
| abstract_inverted_index.which | 64, 78, 125 |
| abstract_inverted_index.(DNNs) | 13 |
| abstract_inverted_index.QuanDA | 110, 190 |
| abstract_inverted_index.Unlike | 102 |
| abstract_inverted_index.checks | 81 |
| abstract_inverted_index.degree | 62 |
| abstract_inverted_index.ensure | 32 |
| abstract_inverted_index.formal | 27 |
| abstract_inverted_index.hidden | 123, 138 |
| abstract_inverted_index.layer. | 145 |
| abstract_inverted_index.neural | 11 |
| abstract_inverted_index.nodes, | 124 |
| abstract_inverted_index.nodes. | 182 |
| abstract_inverted_index.noise. | 23 |
| abstract_inverted_index.safety | 196 |
| abstract_inverted_index.values | 140 |
| abstract_inverted_index.years, | 3 |
| abstract_inverted_index.DNN’s | 44 |
| abstract_inverted_index.QuanDA, | 77 |
| abstract_inverted_index.behaves | 67 |
| abstract_inverted_index.certain | 86 |
| abstract_inverted_index.correct | 16 |
| abstract_inverted_index.desired | 50 |
| abstract_inverted_index.enables | 126 |
| abstract_inverted_index.network | 181 |
| abstract_inverted_index.precise | 61 |
| abstract_inverted_index.propose | 70 |
| abstract_inverted_index.provide | 175 |
| abstract_inverted_index.studies | 5 |
| abstract_inverted_index.whether | 82 |
| abstract_inverted_index.However, | 38 |
| abstract_inverted_index.analysis | 28, 75, 108, 193 |
| abstract_inverted_index.behavior | 45, 87 |
| abstract_inverted_index.enabling | 155 |
| abstract_inverted_index.equipped | 57 |
| abstract_inverted_index.implicit | 115 |
| abstract_inverted_index.networks | 12 |
| abstract_inverted_index.numerous | 4 |
| abstract_inverted_index.presence | 20 |
| abstract_inverted_index.provides | 90, 186 |
| abstract_inverted_index.analysis, | 154 |
| abstract_inverted_index.analysis. | 161 |
| abstract_inverted_index.available | 105 |
| abstract_inverted_index.behavior. | 37, 101 |
| abstract_inverted_index.delineate | 35, 98 |
| abstract_inverted_index.determine | 59 |
| abstract_inverted_index.estimated | 92 |
| abstract_inverted_index.estimates | 178 |
| abstract_inverted_index.framework | 128, 148, 166 |
| abstract_inverted_index.leverages | 149 |
| abstract_inverted_index.motivated | 25 |
| abstract_inverted_index.potential | 187 |
| abstract_inverted_index.propagate | 130 |
| abstract_inverted_index.acceptable | 36 |
| abstract_inverted_index.approaches | 54 |
| abstract_inverted_index.benchmark, | 173 |
| abstract_inverted_index.delineates | 85 |
| abstract_inverted_index.framework, | 76 |
| abstract_inverted_index.high-speed | 156 |
| abstract_inverted_index.particular | 100 |
| abstract_inverted_index.proceeding | 143 |
| abstract_inverted_index.assumptions | 116 |
| abstract_inverted_index.frameworks, | 109 |
| abstract_inverted_index.parallelize | 152 |
| abstract_inverted_index.probability | 93, 119, 134, 177 |
| abstract_inverted_index.properties. | 197 |
| abstract_inverted_index.qualitative | 53 |
| abstract_inverted_index.Furthermore, | 146 |
| abstract_inverted_index.application, | 51 |
| abstract_inverted_index.applications | 188 |
| abstract_inverted_index.demonstrated | 6, 168 |
| abstract_inverted_index.distribution | 120 |
| abstract_inverted_index.quantitative | 73, 106 |
| abstract_inverted_index.reachability | 176 |
| abstract_inverted_index.unacceptable | 47 |
| abstract_inverted_index.applicability | 163 |
| abstract_inverted_index.distributions | 135 |
| abstract_inverted_index.unacceptably. | 68 |
| abstract_inverted_index.vulnerability | 8 |
| abstract_inverted_index.implementation | 158 |
| abstract_inverted_index.classifications | 17 |
| cited_by_percentile_year | |
| countries_distinct_count | 3 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile.value | 0.10125301 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |