Software Verification and Formal Methods for ML-Enabled Autonomous Systems: 5th International Workshop, FoMLAS 2022, and 15th International Workshop, NSV 2022, Haifa, Israel, July 31 - August 1, and August 11, 2022, Proceedings

by Omri Isac (Editor), Radoslav Ivanov (Editor), Guy Katz (Editor), Nina Narodytska (Editor), Laura Nenzi (Editor)

Overview

This book constitutes the refereed proceedings of the 5th International Workshop on Software Verification and Formal Methods for ML-Enables Autonomous Systems, FoMLAS 2022, and the 15th International Workshop on Numerical Software Verification, NSV 2022, which took place in Haifa, Israel, in July/August 2022. 
The volume contains 8 full papers from the FoMLAS 2022 workshop and 3 full papers from the NSV 2022 workshop. The FoMLAS workshop is dedicated to the development of novel formal methods techniques to discussing on how formal methods can be used to increase predictability, explainability, and accountability of ML-enabled autonomous systems. NSV 2022 is focusing on the challenges of the verification of cyber-physical systems with machine learning components. 

Product Details

ISBN-13:	9783031212222
Publisher:	Springer-Verlag New York, LLC
Publication date:	12/15/2022
Series:	Lecture Notes in Computer Science , #13466
Sold by:	Barnes & Noble
Format:	eBook
File size:	17 MB
Note:	This product may take a few minutes to download.

Table of Contents

FoMLAS 2022.- VPN: Verification of Poisoning in Neural Networks.- A Cascade of Checkers for Run-time Certification of Local Robustness.- CEG4N: Counter-Example Guided Neural Network Quantization Refinement .- Minimal Multi-Layer Modifications of Deep Neural Networks.- Differentiable Logics for Neural Network Training and Verification.- Neural Networks in Imandra: Matrix Representation as a Verification Choice.- Self-Correcting Neural Networks For Safe Classification.- Self-Correcting Neural Networks For Safe Classification.- NSV 2022.- Verified Numerical Methods for Ordinary Differential Equations.- Neural Network Precision Tuning Using Stochastic Arithmetic.- MLTL Multi-type (MLTLM): A Logic for Reasoning about Signals of Different Types.