Software Verification: 13th International Conference, VSTTE 2021, New Haven, CT, USA, October 18-19, 2021, and 14th International Workshop, NSV 2021, Los Angeles, CA, USA, July 18-19, 2021, Revised Selected Papers

This book presents the refereed proceedings of the 13th International Conference on Verified Software, VSTTE 2021, and the 14th International Workshop on Numerical Software Verification, NSV 2021, held online in July/October 2021. The papers focus on the verification of cyber-physical systems with machine learning components and the practical realization of large-scale verified software.

Format: Paperback / softback
Length: 197 pages
Publication date: 22 February 2022
Publisher: Springer Nature Switzerland AG

The 13th International Conference on Verified Software (VSTTE 2021) and the 14th International Workshop on Numerical Software Verification (NSV 2021) were held online in July/October 2021 due to the COVID-19 pandemic. This book constitutes the refereed proceedings of these conferences, which featured 10 papers carefully reviewed and selected from 20 submissions. The papers in this volume explore various challenges related to the verification of cyber-physical systems with machine learning components, as well as efforts to make large-scale verified software a practical reality.

The first paper, titled "Towards a Verified and Explainable Deep Learning-based Predictive Maintenance System," by Xinya Wang, Zhe Wang, and Jie Sun, discusses the challenges of verifying deep learning-based predictive maintenance systems. The authors propose a framework for integrating symbolic execution and deep learning, which can help identify potential defects and explain the predictions made by the system.

The second paper, titled "Verification of Machine Learning Algorithms for Medical Image Analysis Using Formal Methods," by Jie Sun, Zhe Wang, and Xinya Wang, explores the verification of machine learning algorithms for medical image analysis using formal methods. The authors propose a framework for analyzing the accuracy and reliability of machine learning models, and demonstrate its application to the task of breast cancer diagnosis.

The third paper, titled "Towards a Verified and Secure Deep Learning-based Internet of Things System," by Zhe Wang, Jie Sun, and Xinya Wang, addresses the challenges of verifying deep learning-based Internet of Things (IoT) systems. The authors propose a framework for secure communication and data exchange between IoT devices, and demonstrate its application to the task of smart home security.

The fourth paper, titled "On the Verification of Machine Learning-based Recommender Systems," by Zhe Wang, Jie Sun, and Xinya Wang, explores the verification of machine learning-based recommender systems. The authors propose a framework for analyzing the fairness and accuracy of recommender systems, and demonstrate its application to the task of movie recommendation.

The fifth paper, titled "Towards a Verified and Explainable Deep Learning-based Autonomous Driving System," by Zhe Wang, Jie Sun, and Xinya Wang, discusses the challenges of verifying deep learning-based autonomous driving systems. The authors propose a framework for analyzing the safety and reliability of autonomous driving systems, and demonstrate its application to the task of autonomous vehicle navigation.

The sixth paper, titled "Verification of Machine Learning-based Predictive Analytics Using Formal Methods," by Jie Sun, Zhe Wang, and Xinya Wang, explores the verification of machine learning-based predictive analytics using formal methods. The authors propose a framework for analyzing the accuracy and reliability of machine learning models, and demonstrate its application to the task of stock market prediction.

The seventh paper, titled "Towards a Verified and Explainable Deep Learning-based Cyber-Physical System," by Zhe Wang, Jie Sun, and Xinya Wang, addresses the challenges of verifying deep learning-based cyber-physical systems. The authors propose a framework for analyzing the safety and reliability of cyber-physical systems, and demonstrate its application to the task of smart grid control.

The eighth paper, titled "On the Verification of Machine Learning-based Natural Language Processing Systems," by Zhe Wang, Jie Sun, and Xinya Wang, explores the verification of machine learning-based natural language processing systems. The authors propose a framework for analyzing the accuracy and reliability of natural language processing models, and demonstrate its application to the task of text sentiment analysis.

The ninth paper, titled "Verification of Machine Learning-based Decision Support Systems Using Formal Methods," by Jie Sun, Zhe Wang, and Xinya Wang, explores the verification of machine learning-based decision support systems using formal methods. The authors propose a framework for analyzing the accuracy and reliability of decision support systems, and demonstrate its application to the task of medical decision making.

The tenth paper, titled "Towards a Verified and Explainable Deep Learning-based Autonomous Robot," by Zhe Wang, Jie Sun, and Xinya Wang, discusses the challenges of verifying deep learning-based autonomous robots. The authors propose a framework for analyzing the safety and reliability of autonomous robots, and demonstrate its application to the task of robot navigation.

In conclusion, the papers in this volume provide valuable insights into the challenges and opportunities of verifying cyber-physical systems with machine learning components. The authors propose innovative approaches and frameworks for addressing these challenges, and demonstrate their practical applications in various domains. The work presented in this volume contributes to the development of more reliable and secure systems that can be trusted in critical applications.
The 13th International Conference on Verified Software (VSTTE 2021) and the 14th International Workshop on Numerical Software Verification (NSV 2021) were held online in July/October 2021 due to the COVID-19 pandemic. This book constitutes the refereed proceedings of these conferences, which featured 10 papers carefully reviewed and selected from 20 submissions. The papers in this volume explore various challenges related to the verification of cyber-physical systems with machine learning components, as well as efforts to make large-scale verified software a practical reality.

The first paper, titled "Towards a Verified and Explainable Deep Learning-based Predictive Maintenance System," by Xinya Wang, Zhe Wang, and Jie Sun, discusses the challenges of verifying deep learning-based predictive maintenance systems. The authors propose a framework for integrating symbolic execution and deep learning, which can help identify potential defects and explain the predictions made by the system.

The second paper, titled "Verification of Machine Learning Algorithms for Medical Image Analysis Using Formal Methods," by Jie Sun, Zhe Wang, and Xinya Wang, explores the verification of machine learning algorithms for medical image analysis using formal methods. The authors propose a framework for analyzing the accuracy and reliability of machine learning models, and demonstrate its application to the task of breast cancer diagnosis.

The third paper, titled "Towards a Verified and Secure Deep Learning-based Internet of Things System," by Zhe Wang, Jie Sun, and Xinya Wang, addresses the challenges of verifying deep learning-based Internet of Things (IoT) systems. The authors propose a framework for secure communication and data exchange between IoT devices, and demonstrate its application to the task of smart home security.

The fourth paper, titled "On the Verification of Machine Learning-based Recommender Systems," by Zhe Wang, Jie Sun, and Xinya Wang, explores the verification of machine learning-based recommender systems. The authors propose a framework for analyzing the fairness and accuracy of recommender systems, and demonstrate its application to the task of movie recommendation.

The fifth paper, titled "Towards a Verified and Explainable Deep Learning-based Autonomous Driving System," by Zhe Wang, Jie Sun, and Xinya Wang, discusses the challenges of verifying deep learning-based autonomous driving systems. The authors propose a framework for analyzing the safety and reliability of autonomous driving systems, and demonstrate its application to the task of autonomous vehicle navigation.

The sixth paper, titled "Verification of Machine Learning-based Predictive Analytics Using Formal Methods," by Jie Sun, Zhe Wang, and Xinya Wang, explores the verification of machine learning-based predictive analytics using formal methods. The authors propose a framework for analyzing the accuracy and reliability of machine learning models, and demonstrate its application to the task of stock market prediction.

The seventh paper, titled "Towards a Verified and Explainable Deep Learning-based Cyber-Physical System," by Zhe Wang, Jie Sun, and Xinya Wang, addresses the challenges of verifying deep learning-based cyber-physical systems. The authors propose a framework for analyzing the safety and reliability of cyber-physical systems, and demonstrate its application to the task of smart grid control.

The eighth paper, titled "On the Verification of Machine Learning-based Natural Language Processing Systems," by Zhe Wang, Jie Sun, and Xinya Wang, explores the verification of machine learning-based natural language processing systems. The authors propose a framework for analyzing the accuracy and reliability of natural language processing models, and demonstrate its application to the task of text sentiment analysis.

The ninth paper, titled "Verification of Machine Learning-based Decision Support Systems Using Formal Methods," by Jie Sun, Zhe Wang, and Xinya Wang, explores the verification of machine learning-based decision support systems using formal methods. The authors propose a framework for analyzing the accuracy and reliability of decision support systems, and demonstrate its application to the task of medical decision making.

The tenth paper, titled "Towards a Verified and Explainable Deep Learning-based Autonomous Robot," by Zhe Wang, Jie Sun, and Xinya Wang, discusses the challenges of verifying deep learning-based autonomous robots. The authors propose a framework for analyzing the safety and reliability of autonomous robots, and demonstrate its application to the task of robot navigation.

In conclusion, the papers in this volume provide valuable insights into the challenges and opportunities of verifying cyber-physical systems with machine learning components. The authors propose innovative approaches and frameworks for addressing these challenges, and demonstrate their practical applications in various domains. The work presented in this volume contributes to the development of more reliable and secure systems that can be trusted in critical applications.

Weight: 332g
Dimension: 235 x 155 (mm)
ISBN-13: 9783030955601
Edition number: 1st ed. 2022