Pub Date : 2023-06-30DOI: 10.1007/s10009-023-00707-0
Stefan Schupp, E. Ábrahám, Md Tawhid Bin Waez, Thomas Rambow, Zeng Qiu
{"title":"On the applicability of hybrid systems safety verification tools from the automotive perspective","authors":"Stefan Schupp, E. Ábrahám, Md Tawhid Bin Waez, Thomas Rambow, Zeng Qiu","doi":"10.1007/s10009-023-00707-0","DOIUrl":"https://doi.org/10.1007/s10009-023-00707-0","url":null,"abstract":"","PeriodicalId":14395,"journal":{"name":"International Journal on Software Tools for Technology Transfer","volume":"36 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81050947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-30DOI: 10.1007/s10009-023-00711-4
Konstantin Kueffner, Anna Lukina, Christian Schilling, Thomas A. Henzinger
Abstract Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where inputs frequently fall outside the fixed set of initially known classes, remains a challenge. We consider the problem of monitoring the classification decisions of neural networks in the presence of novel classes. For this purpose, we generalize our recently proposed abstraction-based monitor from binary output to real-valued quantitative output. This quantitative output enables new applications, two of which we investigate in the paper. As our first application, we introduce an algorithmic framework for active monitoring of a neural network, which allows us to learn new classes dynamically and yet maintain high monitoring performance. As our second application, we present an offline procedure to retrain the neural network to improve the monitor’s detection performance without deteriorating the network’s classification accuracy. Our experimental evaluation demonstrates both the benefits of our active monitoring framework in dynamic scenarios and the effectiveness of the retraining procedure.
{"title":"Into the unknown: active monitoring of neural networks (extended version)","authors":"Konstantin Kueffner, Anna Lukina, Christian Schilling, Thomas A. Henzinger","doi":"10.1007/s10009-023-00711-4","DOIUrl":"https://doi.org/10.1007/s10009-023-00711-4","url":null,"abstract":"Abstract Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where inputs frequently fall outside the fixed set of initially known classes, remains a challenge. We consider the problem of monitoring the classification decisions of neural networks in the presence of novel classes. For this purpose, we generalize our recently proposed abstraction-based monitor from binary output to real-valued quantitative output. This quantitative output enables new applications, two of which we investigate in the paper. As our first application, we introduce an algorithmic framework for active monitoring of a neural network, which allows us to learn new classes dynamically and yet maintain high monitoring performance. As our second application, we present an offline procedure to retrain the neural network to improve the monitor’s detection performance without deteriorating the network’s classification accuracy. Our experimental evaluation demonstrates both the benefits of our active monitoring framework in dynamic scenarios and the effectiveness of the retraining procedure.","PeriodicalId":14395,"journal":{"name":"International Journal on Software Tools for Technology Transfer","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135857635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-26DOI: 10.1007/s10009-023-00713-2
N. Shafiei, K. Havelund, P. Mehlitz
{"title":"Concurrent runtime verification of data rich events","authors":"N. Shafiei, K. Havelund, P. Mehlitz","doi":"10.1007/s10009-023-00713-2","DOIUrl":"https://doi.org/10.1007/s10009-023-00713-2","url":null,"abstract":"","PeriodicalId":14395,"journal":{"name":"International Journal on Software Tools for Technology Transfer","volume":"2 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87832889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-22DOI: 10.1007/s10009-023-00705-2
J. Kosińska, Grzegorz Brotoń, Maciej Tobiasz
{"title":"Knowledge representation of the state of a cloud-native application","authors":"J. Kosińska, Grzegorz Brotoń, Maciej Tobiasz","doi":"10.1007/s10009-023-00705-2","DOIUrl":"https://doi.org/10.1007/s10009-023-00705-2","url":null,"abstract":"","PeriodicalId":14395,"journal":{"name":"International Journal on Software Tools for Technology Transfer","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90594833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-22DOI: 10.1007/s10009-023-00706-1
K. Havelund, G. Holzmann
{"title":"Programming event monitors","authors":"K. Havelund, G. Holzmann","doi":"10.1007/s10009-023-00706-1","DOIUrl":"https://doi.org/10.1007/s10009-023-00706-1","url":null,"abstract":"","PeriodicalId":14395,"journal":{"name":"International Journal on Software Tools for Technology Transfer","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79106651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1007/s10009-023-00716-z
Florian Jüngermann, Jan Křetínský, Maximilian Weininger
Abstract Recently, decision trees (DT) have been used as an explainable representation of controllers (a.k.a. strategies, policies, schedulers). Although they are often very efficient and produce small and understandable controllers for discrete systems, complex continuous dynamics still pose a challenge. In particular, when the relationships between variables take more complex forms, such as polynomials, they cannot be obtained using the available DT learning procedures. In contrast, support vector machines provide a more powerful representation, capable of discovering many such relationships, but not in an explainable form. Therefore, we suggest to combine the two frameworks to obtain an understandable representation over richer, domain-relevant algebraic predicates. We demonstrate and evaluate the proposed method experimentally on established benchmarks.
{"title":"Algebraically explainable controllers: decision trees and support vector machines join forces","authors":"Florian Jüngermann, Jan Křetínský, Maximilian Weininger","doi":"10.1007/s10009-023-00716-z","DOIUrl":"https://doi.org/10.1007/s10009-023-00716-z","url":null,"abstract":"Abstract Recently, decision trees (DT) have been used as an explainable representation of controllers (a.k.a. strategies, policies, schedulers). Although they are often very efficient and produce small and understandable controllers for discrete systems, complex continuous dynamics still pose a challenge. In particular, when the relationships between variables take more complex forms, such as polynomials, they cannot be obtained using the available DT learning procedures. In contrast, support vector machines provide a more powerful representation, capable of discovering many such relationships, but not in an explainable form. Therefore, we suggest to combine the two frameworks to obtain an understandable representation over richer, domain-relevant algebraic predicates. We demonstrate and evaluate the proposed method experimentally on established benchmarks.","PeriodicalId":14395,"journal":{"name":"International Journal on Software Tools for Technology Transfer","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135046167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-30DOI: 10.1007/s10009-023-00704-3
Thom Badings, Thiago D. Simão, Marnix Suilen, Nils Jansen
Abstract This position paper reflects on the state-of-the-art in decision-making under uncertainty. A classical assumption is that probabilities can sufficiently capture all uncertainty in a system. In this paper, the focus is on the uncertainty that goes beyond this classical interpretation, particularly by employing a clear distinction between aleatoric and epistemic uncertainty. The paper features an overview of Markov decision processes (MDPs) and extensions to account for partial observability and adversarial behavior. These models sufficiently capture aleatoric uncertainty, but fail to account for epistemic uncertainty robustly. Consequently, we present a thorough overview of so-called uncertainty models that exhibit uncertainty in a more robust interpretation. We show several solution techniques for both discrete and continuous models, ranging from formal verification, over control-based abstractions, to reinforcement learning. As an integral part of this paper, we list and discuss several key challenges that arise when dealing with rich types of uncertainty in a model-based fashion.
{"title":"Decision-making under uncertainty: beyond probabilities","authors":"Thom Badings, Thiago D. Simão, Marnix Suilen, Nils Jansen","doi":"10.1007/s10009-023-00704-3","DOIUrl":"https://doi.org/10.1007/s10009-023-00704-3","url":null,"abstract":"Abstract This position paper reflects on the state-of-the-art in decision-making under uncertainty. A classical assumption is that probabilities can sufficiently capture all uncertainty in a system. In this paper, the focus is on the uncertainty that goes beyond this classical interpretation, particularly by employing a clear distinction between aleatoric and epistemic uncertainty. The paper features an overview of Markov decision processes (MDPs) and extensions to account for partial observability and adversarial behavior. These models sufficiently capture aleatoric uncertainty, but fail to account for epistemic uncertainty robustly. Consequently, we present a thorough overview of so-called uncertainty models that exhibit uncertainty in a more robust interpretation. We show several solution techniques for both discrete and continuous models, ranging from formal verification, over control-based abstractions, to reinforcement learning. As an integral part of this paper, we list and discuss several key challenges that arise when dealing with rich types of uncertainty in a model-based fashion.","PeriodicalId":14395,"journal":{"name":"International Journal on Software Tools for Technology Transfer","volume":"295 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135478143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-30DOI: 10.1007/s10009-023-00702-5
Alnis Murtovi, Alexander Bainczyk, Gerrit Nolte, Maximilian Schlüter, Bernhard Steffen
Abstract In this paper, we present Forest GUMP (for Generalized, Unifying Merge Process) a tool for verification and precise explanation of Random forests. Besides pre/post-condition-based verification and equivalence checking, Forest GUMP also supports three concepts of explanation, the well-known model explanation and outcome explanation , as well as class characterization , i.e., the precise characterization of all samples that are equally classified. Key technology to achieve these results is algebraic aggregation, i.e., the transformation of a Random Forest into a semantically equivalent, concise white-box representation in terms of Algebraic Decision Diagrams (ADDs). The paper sketches the method and demonstrates the use of Forest GUMP along illustrative examples. This way readers should acquire an intuition about the tool, and the way how it should be used to increase the understanding not only of the considered dataset, but also of the character of Random Forests and the ADD technology, here enriched to comprise infeasible path elimination. As Forest GUMP is publicly available all experiments can be reproduced, modified, and complemented using any dataset that is available in the ARFF format.
{"title":"Forest GUMP: a tool for verification and explanation","authors":"Alnis Murtovi, Alexander Bainczyk, Gerrit Nolte, Maximilian Schlüter, Bernhard Steffen","doi":"10.1007/s10009-023-00702-5","DOIUrl":"https://doi.org/10.1007/s10009-023-00702-5","url":null,"abstract":"Abstract In this paper, we present Forest GUMP (for Generalized, Unifying Merge Process) a tool for verification and precise explanation of Random forests. Besides pre/post-condition-based verification and equivalence checking, Forest GUMP also supports three concepts of explanation, the well-known model explanation and outcome explanation , as well as class characterization , i.e., the precise characterization of all samples that are equally classified. Key technology to achieve these results is algebraic aggregation, i.e., the transformation of a Random Forest into a semantically equivalent, concise white-box representation in terms of Algebraic Decision Diagrams (ADDs). The paper sketches the method and demonstrates the use of Forest GUMP along illustrative examples. This way readers should acquire an intuition about the tool, and the way how it should be used to increase the understanding not only of the considered dataset, but also of the character of Random Forests and the ADD technology, here enriched to comprise infeasible path elimination. As Forest GUMP is publicly available all experiments can be reproduced, modified, and complemented using any dataset that is available in the ARFF format.","PeriodicalId":14395,"journal":{"name":"International Journal on Software Tools for Technology Transfer","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135477898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-30DOI: 10.1007/s10009-023-00700-7
Maximilian Schlüter, Gerrit Nolte, Alnis Murtovi, Bernhard Steffen
Abstract In this paper, we present an algebraic approach to the precise and global verification and explanation of Rectifier Neural Networks , a subclass of Piece-wise Linear Neural Networks (PLNNs), i.e., networks that semantically represent piece-wise affine functions. Key to our approach is the symbolic execution of these networks that allows the construction of semantically equivalent Typed Affine Decision Structures (TADS). Due to their deterministic and sequential nature, TADS can, similarly to decision trees, be considered as white-box models and therefore as precise solutions to the model and outcome explanation problem. TADS are linear algebras, which allows one to elegantly compare Rectifier Networks for equivalence or similarity, both with precise diagnostic information in case of failure, and to characterize their classification potential by precisely characterizing the set of inputs that are specifically classified, or the set of inputs where two network-based classifiers differ. All phenomena are illustrated along a detailed discussion of a minimal, illustrative example: the continuous XOR function.
{"title":"Towards rigorous understanding of neural networks via semantics-preserving transformations","authors":"Maximilian Schlüter, Gerrit Nolte, Alnis Murtovi, Bernhard Steffen","doi":"10.1007/s10009-023-00700-7","DOIUrl":"https://doi.org/10.1007/s10009-023-00700-7","url":null,"abstract":"Abstract In this paper, we present an algebraic approach to the precise and global verification and explanation of Rectifier Neural Networks , a subclass of Piece-wise Linear Neural Networks (PLNNs), i.e., networks that semantically represent piece-wise affine functions. Key to our approach is the symbolic execution of these networks that allows the construction of semantically equivalent Typed Affine Decision Structures (TADS). Due to their deterministic and sequential nature, TADS can, similarly to decision trees, be considered as white-box models and therefore as precise solutions to the model and outcome explanation problem. TADS are linear algebras, which allows one to elegantly compare Rectifier Networks for equivalence or similarity, both with precise diagnostic information in case of failure, and to characterize their classification potential by precisely characterizing the set of inputs that are specifically classified, or the set of inputs where two network-based classifiers differ. All phenomena are illustrated along a detailed discussion of a minimal, illustrative example: the continuous XOR function.","PeriodicalId":14395,"journal":{"name":"International Journal on Software Tools for Technology Transfer","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135478139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：