A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability

X Huang, D Kroening, W Ruan, J Sharp, Y Sun… - Computer Science …, 2020 - Elsevier
In the past few years, significant progress has been made on deep neural networks (DNNs)
in achieving human-level performance on several long-standing tasks. With the broader …
被引用次数：511 相关文章
[PDF] qub.ac.uk

[PDF][PDF] A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability

X Huang, D Kroening, W Ruan, J Sharp, Y Sun… - 2020 - pureadmin.qub.ac.uk
In the past few years, significant progress has been made in the development of deep neural
networks (DNNs), which now outperform humans in several difficult tasks, such as image …
[PDF] github.io

[PDF][PDF] A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability

X Huang, D Kroening, W Ruan, J Sharp, Y Sun… - 2020 - nguyenthanhvuh.github.io
In the past few years, significant progress has been made in the development of deep neural
networks (DNNs), which now outperform humans in several difficult tasks, such as image …

A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability

X Huang, D Kroening, W Ruan… - Computer …, 2020 - research.manchester.ac.uk
In the past few years, significant progress has been made on deep neural networks (DNNs)
in achieving human-level performance on several long-standing tasks. With the broader …
[PDF] core.ac.uk

[PDF][PDF] Safety and Trustworthiness of Deep Neural Networks: A Survey

X Huang, D Kroening, M Kwiatkowska… - arXiv preprint arXiv …, 2018 - core.ac.uk
In the past few years, significant progress has been made on deep neural networks (DNNs)
in achieving human-level intelligence on several long-standing tasks such as image …
[PDF] tu-dortmund.de

[PDF][PDF] A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability

X Huang, D Kroening, W Ruan… - arXiv preprint …, 2018 - www-ai.cs.tu-dortmund.de
In the past few years, significant progress has been made in the development of deep neural
networks (DNNs), which now outperform humans in several difficult tasks, such as image …

A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability

X Huang, D Kroening, W Ruan, J Sharp, Y Sun… - arXiv e …, 2018 - ui.adsabs.harvard.edu
In the past few years, significant progress has been made on deep neural networks (DNNs)
in achieving human-level performance on several long-standing tasks. With the broader …

[引用][C] A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability

X Huang, D Kroening, W Ruan, J Sharp, Y Sun… - Computer Science …, 2020 - cir.nii.ac.jp
A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial
attack and defence, and interpretability | CiNii Research CiNii 国立情報学研究所 学術情報 …

A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability?

X Huang, D Kroening, W Ruan… - COMPUTER …, 2020 - livrepository.liverpool.ac.uk
In the past few years, significant progress has been made on deep neural networks (DNNs)
in achieving human-level performance on several long-standing tasks. With the broader …

A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability

X Huang, D Kroening, W Ruan, J Sharp, Y Sun… - arXiv preprint arXiv …, 2018 - arxiv.org
In the past few years, significant progress has been made on deep neural networks (DNNs)
in achieving human-level performance on several long-standing tasks. With the broader …