Activity
From 05/27/2021 to 06/25/2021
06/21/2021
- 01:24 PM Document: Assuring Learning-Enabled Components in Small Unmanned Aircraft Systems
Krishna Muvva, Justin M. Bradley, Marilyn Wolf, Taylor T. Johnson, "Assuring Learning-Enabled Compon...- 01:22 PM Document: Verification of Neural Network Compression of ACAS Xu Lookup Tables with Star Set Reachability
Diego Manzanas Lopez, Taylor T. Johnson, Hoang-Dung Tran, Stanley Bak, Xin Chen, Kerianne Hobbs, "Verification of Neu...
06/14/2021
- 01:13 PM Document: Reachable Set Estimation for Neural Network Control Systems: A Simulation-Guided Approach
Weiming Xiang, Hoang-Dung Tran, Xiaodong Yang, Taylor T. Johnson, "Reachable Set Estimation for Neural Network Contro...
- 01:12 PM Document: Robustness Verification of Semantic Segmentation Neural Networks using Relaxed Reachability
Hoang-Dung Tran, Neelanjana Pal, Patrick Musau, Xiaodong Yang, Nathaniel P. Hamilton, Diego Manzanas Lopez, Stanley B...
- 09:56 AM Document: Detection of Dataset Shifts in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
Cyber-physical systems (CPSs) use learning-enabled components (LECs) extensively to cope with various complex tasks u...
- 11:39 PM Document: Assurance monitoring of learning-enabled cyber-physical systems using inductive conformal prediction based on distance learning
Machine learning components such as deep neural networks are used extensively in Cyber-Physical Systems (CPS). Howeve...
06/13/2021
- 12:37 PM Document: Deep-RBF Networks for Anomaly Detection in Automotive Cyber-Physical Systems
Deep Neural Networks (DNNs) are widely used in automotive Cyber-Physical Systems (CPS) to implement autonomy related ...
Arxiv copy (Paper to appear at Smartcomp 2021)
- 12:34 PM Document: ReSonAte: A Runtime Risk Assessment Framework for Autonomous Systems
Hazard analysis and assurance cases are well-established approaches for assessing the safety of cyber-physical system...
Arxiv Copy (Paper Accepted at SEAMS 2021)
06/07/2021
- 03:21 PM Document: Improving Prediction Confidence in Learning-Enabled Autonomous Systems
Autonomous systems use extensively learning-enabled components such as deep neural networks (DNNs) for prediction and...
Also available in: Atom