Enhancing robustness verification for deep neural networks via symbolic propagation

P Yang, J Li, J Liu, CC Huang, R Li, L Chen… - Formal Aspects of …, 2021 - Springer
Deep neural networks (DNNs) have been shown lack of robustness, as they are vulnerable
to small perturbations on the inputs. This has led to safety concerns on applying DNNs to …
被引用次数：19 相关文章

Enhancing Robustness Verification for Deep Neural Networks via Symbolic Propagation

P Yang, J Li, J Liu, CC Huang, R Li, L Chen… - Formal Aspects of …, 2021 - dl.acm.org
Deep neural networks (DNNs) have been shown lack of robustness, as they are vulnerable
to small perturbations on the inputs. This has led to safety concerns on applying DNNs to …
[PDF] core.ac.uk

[PDF][PDF] Enhancing Robustness Verification for Deep Neural Networks via Symbolic Propagation

P Yang, J Li, J Liu, CC Huang, R Li, L Chen, X Huang… - core.ac.uk
Deep neural networks (DNNs) have been shown lack of robustness, as they are vulnerable
to small perturbations on the inputs. This has led to safety concerns on applying DNNs to …
[PDF] github.io

[PDF][PDF] Enhancing Robustness Verification for Deep Neural Networks via Symbolic Propagation

P Yang, J Li, J Liu, CC Huang, R Li, L Chen, X Huang… - lqchen.github.io
Deep neural networks (DNNs) have been shown lack of robustness, as they are vulnerable
to small perturbations on the inputs. This has led to safety concerns on applying DNNs to …
[HTML] itsbahrain.com

[HTML][HTML] Enhancing Robustness Verification for Deep Neural Networks via Symbolic Propagation

P Yang, J Li, J Liu, CC Huang, R Li, L Chen… - Formal Aspects of …, 2021 - itsbahrain.com
Deep neural networks (DNNs) have been shown lack of robustness, as they are vulnerable
to small perturbations on the inputs. This has led to safety concerns on applying DNNs to …
[PDF] github.io

[PDF][PDF] Enhancing Robustness Verification for Deep Neural Networks via Symbolic Propagation

P Yang, J Li, J Liu, CC Huang, R Li, L Chen, X Huang… - lqchen.github.io
Deep neural networks (DNNs) have been shown lack of robustness, as they are vulnerable
to small perturbations on the inputs. This has led to safety concerns on applying DNNs to …