Neural Network Compression of ACAS Xu Early Prototype Is Unsafe: Closed-Loop Verification Through Quantized State Backreachability-Reference-Cited by-同舟云学术

Neural Network Compression of ACAS Xu Early Prototype Is Unsafe: Closed-Loop Verification Through Quantized State Backreachability

Published:2022 Issue: Volume: Page:280-298
ISSN:0302-9743
Container-title:Lecture Notes in Computer Science
language:
Short-container-title:

Author:

Bak Stanley,Tran Hoang-Dung

Publisher

Springer International Publishing

Link

https://link.springer.com/content/pdf/10.1007/978-3-031-06773-0_15

Reference34 articles.

1. Lecture Notes in Computer Science;S Bak,2021

2. Bak, S., Duggirala, P.S.: HyLAA: a tool for computing simulation-equivalent reachability for linear systems. In: Proceedings of the 20th International Conference on Hybrid Systems: Computation and Control. HSCC 2017 (2017)

3. Bak, S., Liu, C., Johnson, T.: The second international verification of neural networks competition (VNN-COMP 2021): Summary and results. arXiv preprint arXiv:2109.00498 (2021)

4. Lecture Notes in Computer Science;S Bak,2020

5. Bak, S., Tran, H.D., Johnson, T.T.: Numerical verification of affine systems with up to a billion dimensions. In: Proceedings of the 22Nd ACM International Conference on Hybrid Systems: Computation and Control, pp. 23–32. HSCC 2019. ACM, New York, NY, USA (2019)

Cited by 6 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. Assured Collision Avoidance for Learned Controllers: A Case Study of ACAS Xu;AIAA SCITECH 2024 Forum;2024-01-04

2. The Inverse Problem for Neural Networks;Bridging the Gap Between AI and Reality;2023-12-14

3. Rich and Expressive Specification of Continuous-Learning Cyber-Physical Systems;2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume (DSN-S);2023-06

4. Reachability Analysis for Linear Systems with Uncertain Parameters using Polynomial Zonotopes;Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control;2023-05-09

5. DRIP: Domain Refinement Iteration With Polytopes for Backward Reachability Analysis of Neural Feedback Loops;IEEE Control Systems Letters;2023