A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximation-Reference-Cited by-同舟云学术

A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximation

Published:2023-07-12 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis
language:
Short-container-title:

Author:

Xue Zhiyi¹,Liu Si²,Zhang Zhaodi³,Wu Yiting¹,Zhang Min¹

Affiliation:

1. East China Normal University, China

2. ETH Zurich, Switzerland

3. Chengdu Education Research Institute, China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3597926.3598127

Reference59 articles.

1. Apollo. 2017. ApolloAuto. https://github.com/ApolloAuto/apollo Accessed: 2022-05-06 Apollo. 2017. ApolloAuto. https://github.com/ApolloAuto/apollo Accessed: 2022-05-06

2. Probabilistic verification of fairness properties via concentration

3. Mariusz Bojarski , Davide Del Testa , Daniel Dworakowski, Bernhard Firner , Beat Flepp, Prasoon Goyal, Lawrence D. Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, Xin Zhang, Jake Zhao, and Karol Zieba. 2016 . End to End Learning for Self-Driving Cars. CoRR , abs/1604.07316 (2016), https://doi.org/10.48550/arXiv.1604.07316 arxiv:1604.07316. 10.48550/arXiv.1604.07316 Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal, Lawrence D. Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, Xin Zhang, Jake Zhao, and Karol Zieba. 2016. End to End Learning for Self-Driving Cars. CoRR, abs/1604.07316 (2016), https://doi.org/10.48550/arXiv.1604.07316 arxiv:1604.07316.

4. Towards Evaluating the Robustness of Neural Networks

5. Anirban Chakraborty , Manaar Alam , Vishal Dey , Anupam Chattopadhyay , and Debdeep Mukhopadhyay . 2018. Adversarial Attacks and Defences: A Survey. CoRR, abs/1810.00069 ( 2018 ), https://doi.org/10.48550/arXiv.1810.00069 10.48550/arXiv.1810.00069 Anirban Chakraborty, Manaar Alam, Vishal Dey, Anupam Chattopadhyay, and Debdeep Mukhopadhyay. 2018. Adversarial Attacks and Defences: A Survey. CoRR, abs/1810.00069 (2018), https://doi.org/10.48550/arXiv.1810.00069

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. A Dual Relaxation Method for Neural Network Verification;International Journal of Software Engineering and Knowledge Engineering;2024-05-27

2. A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximation;Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis;2023-07-12