Distribution Models for Falsification and Verification of DNNs-Reference-Cited by-同舟云学术

Distribution Models for Falsification and Verification of DNNs

Published:2021-11 Issue: Volume: Page:
ISSN:
Container-title:2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)
language:
Short-container-title:

Author:

Toledo Felipe,Shriver David,Elbaum Sebastian,Dwyer Matthew B.

Funder

National Science Foundation

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9678507/9678392/09678590.pdf?arnumber=9678590

Reference67 articles.

1. DroNet: Learning to Fly by Driving

2. DNNV: A Framework for Deep Neural Network Verification

3. Towards fast computation of certified robustness for relu networks;weng;ICML ser Proceedings of Machine Learning Research,2018

4. Provable defenses against adversarial examples via the convex outer adversarial polytope;wong;ICML ser Proceedings of Machine Learning Research,2018

5. Evaluating robustness of neural networks with mixed integer programming;tjeng,0

Cited by 5 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. Hierarchical Distribution-aware Testing of Deep Learning;ACM Transactions on Software Engineering and Methodology;2023-12-21

2. What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety-Critical Systems;Bridging the Gap Between AI and Reality;2023-12-14

3. Deeper Notions of Correctness in Image-Based DNNs: Lifting Properties from Pixel to Entities;Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering;2023-11-30

4. DistXplore: Distribution-Guided Testing for Evaluating and Enhancing Deep Learning Systems;Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering;2023-11-30

5. Characterizing the Complexity and Its Impact on Testing in ML-Enabled Systems : A Case Sutdy on Rasa;2023 IEEE International Conference on Software Maintenance and Evolution (ICSME);2023-10-01