{"title":"Automatic Abstraction Refinement in Neural Network Verification using Sensitivity Analysis","authors":"Tobias Ladner, M. Althoff","doi":"10.1145/3575870.3587129","DOIUrl":"https://doi.org/10.1145/3575870.3587129","url":null,"abstract":"The formal verification of neural networks is essential for their application in safety-critical environments. However, the set-based verification of neural networks using linear approximations often obtains overly conservative results, while nonlinear approximations quickly become computationally infeasible in deep neural networks. We address this issue for the first time by automatically balancing between precision and computation time without splitting the propagated set. Our work introduces a novel automatic abstraction refinement approach using sensitivity analysis to iteratively reduce the abstraction error at the neuron level until either the specifications are met or a maximum number of iterations is reached. Our evaluation shows that we can tightly over-approximate the output sets of deep neural networks and that our approach is up to a thousand times faster than a naive approach. We further demonstrate the applicability of our approach in closed-loop settings.","PeriodicalId":426801,"journal":{"name":"Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128643382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Qi Heng Ho, Roland Ilyes, Zachary Sunberg, Morteza Lahijanian
{"title":"Poster Abstract: Sampling-based Approach to Robust STL Synthesis for Complex Systems under Uncertainty","authors":"Qi Heng Ho, Roland Ilyes, Zachary Sunberg, Morteza Lahijanian","doi":"10.1145/3575870.3589551","DOIUrl":"https://doi.org/10.1145/3575870.3589551","url":null,"abstract":"ACM Reference Format: Qi Heng Ho, Roland B. Ilyes, Zachary Sunberg, and Morteza Lahijanian. 2023. Poster Abstract: Sampling-based Approach to Robust STL Synthesis for Complex Systems under Uncertainty. In Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control (HSCC ’23), May 9–12, 2023, San Antonio, TX, USA. ACM, New York, NY, USA, 2 pages. https://doi.org/10.1145/3575870.3589551","PeriodicalId":426801,"journal":{"name":"Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114087285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lucas N. Egidio, S. Nayak, M. D. Rossa, Anne-Kathrin Schmuck, R. Jungers
{"title":"Poster Abstract: Towards Seamless Reactivity of Hybrid Control","authors":"Lucas N. Egidio, S. Nayak, M. D. Rossa, Anne-Kathrin Schmuck, R. Jungers","doi":"10.1145/3575870.3589553","DOIUrl":"https://doi.org/10.1145/3575870.3589553","url":null,"abstract":"This poster presents a new technique to synthesize a reactive hybrid controller which actuates a non-linear control system in response to external logical inputs to fulfill an omega-regular specification over a finite set of logical input and observation predicates.","PeriodicalId":426801,"journal":{"name":"Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126407879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reachability Analysis for Linear Systems with Uncertain Parameters using Polynomial Zonotopes","authors":"Ertai Luo, Niklas Kochdumper, Stanley Bak","doi":"10.1145/3575870.3587130","DOIUrl":"https://doi.org/10.1145/3575870.3587130","url":null,"abstract":"In real world applications, uncertain parameters are the rule rather than the exception. We present a reachability algorithm for linear systems with uncertain parameters and inputs using set propagation of polynomial zonotopes. In contrast to previous methods, our approach is able to tightly capture the non-convexity of the reachable set. Building up on our main result, we show how our reachability algorithm can be extended to handle linear time-varying systems as well as linear systems with time-varying parameters. Moreover, our approach opens up new possibilities for reachability analysis of linear time-invariant systems, nonlinear systems, and hybrid systems. We compare our approach to other state of the art methods, with superior tightness on two benchmarks including a 9-dimensional vehicle platooning system.","PeriodicalId":426801,"journal":{"name":"Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131021622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Poster: Convex Scenario Optimisation for ReLU Networks","authors":"Andrea Peruffo, Manuel Mazo Jr.","doi":"10.1145/3575870.3589552","DOIUrl":"https://doi.org/10.1145/3575870.3589552","url":null,"abstract":"","PeriodicalId":426801,"journal":{"name":"Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121430649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Lazy Synthesis of Symbolic Output-Feedback Controllers for State-Based Safety Specifications","authors":"Mehrdad Zareian, Anne-Kathrin Schmuck","doi":"10.1145/3575870.3587111","DOIUrl":"https://doi.org/10.1145/3575870.3587111","url":null,"abstract":"This short paper presents a lazy symbolic output-feedback controller synthesis algorithm for state-based safety specifications over large transition systems. The novel idea of our approach is to integrate an iterative algorithm for observer design with an online adaptable safety controller synthesis algorithm. This allows us to iteratively update the safety controller to observer refinements and to guide these refinements by the existing controller. This results in efficient lazy synthesis of a safety controller whose domain increases with the time spent in synthesis. We present simulation results for a synthetic robot motion planning example showing the benefits of our algorithm compared to the standard approach.","PeriodicalId":426801,"journal":{"name":"Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control","volume":"126 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114009276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Demo Abstract: Analysing CPS Security with Falsification on the Microsoft Flight Simulator","authors":"Tanmay Khandait, Aniruddh Chandratre, Walstan Baptista, Giulia Pedrielli, Georgios Fainekos","doi":"10.1145/3575870.3589550","DOIUrl":"https://doi.org/10.1145/3575870.3589550","url":null,"abstract":"In the paper titled \" Stealthy attacks formalized as STL formulas for Falsification of CPS Security\", we investigate a broad class of attacks on the sensor and actuation blocks in the form of additive perturbation that impacts the measurement and control, respectively. In this demo, we demonstrate the usage of our framework and the underlying technologies along with a case study on aviation systems using Microsoft Flight Simulator (MSFS).","PeriodicalId":426801,"journal":{"name":"Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121041000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mark Wetzlinger, Niklas Kochdumper, Stanley Bak, M. Althoff
{"title":"Fully-Automated Verification of Linear Systems Using Reachability Analysis with Support Functions","authors":"Mark Wetzlinger, Niklas Kochdumper, Stanley Bak, M. Althoff","doi":"10.1145/3575870.3587121","DOIUrl":"https://doi.org/10.1145/3575870.3587121","url":null,"abstract":"While reachability analysis is one of the major techniques for formal verification of dynamical systems, the requirement to adequately tune algorithm parameters often prevents its widespread use in practical applications. In this work, we fully automate the verification process for linear time-invariant systems: Based on the computation of tight upper and lower bounds for the support function of the reachable set along a given direction, we present a fully-automated verification algorithm, which is based on iterative refinement of the upper and lower bounds and thus always returns the correct result in decidable cases. While this verification algorithm is particularly well suited for cases where the specifications are represented by halfspace constraints, we extend it to arbitrary convex unsafe sets using the Gilbert-Johnson-Keerthi algorithm. In summary, our automated verifier is applicable to arbitrary convex initial sets, input sets, as well as unsafe sets, can handle time-varying inputs, automatically returns a counterexample in case of a safety violation, and scales to previously unanalyzable high-dimensional state spaces. Our evaluation on several challenging benchmarks shows significant improvements in computational efficiency compared to verification using other state-of-the-art reachability tools.","PeriodicalId":426801,"journal":{"name":"Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130163707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Poster Abstract: Permissiveness for Strategy Adaptation","authors":"Ashwani Anand, S. Nayak, Anne-Kathrin Schmuck","doi":"10.1145/3575870.3589555","DOIUrl":"https://doi.org/10.1145/3575870.3589555","url":null,"abstract":"This paper presents a new method to automatically compute permissive strategies and permissive assumptions in ω -regular two-player games on graphs to enable strategy adaptation both during synthesis and execution of distributed symbolic controllers.","PeriodicalId":426801,"journal":{"name":"Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126245069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Quantitative Verification for Neural Networks using ProbStars","authors":"Hoang-Dung Tran, Sungwoo Choi, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos, D. Prokhorov","doi":"10.1145/3575870.3587112","DOIUrl":"https://doi.org/10.1145/3575870.3587112","url":null,"abstract":"Most deep neural network (DNN) verification research focuses on qualitative verification, which answers whether or not a DNN violates a safety/robustness property. This paper proposes an approach to convert qualitative verification into quantitative verification for neural networks. The resulting quantitative verification method not only can answer YES or NO questions but also can compute the probability of a property being violated. To do that, we introduce the concept of a probabilistic star (or shortly ProbStar), a new variant of the well-known star set, in which the predicate variables belong to a Gaussian distribution and propose an approach to compute the probability of a probabilistic star in high-dimensional space. Unlike existing works dealing with constrained input sets, our work considers the input set as a truncated multivariate normal (Gaussian) distribution, i.e., besides the constraints on the input variables, the input set has a probability of the constraints being satisfied. The input distribution is represented as a probabilistic star set and is propagated through a network to construct the output reachable set containing multiple ProbStars, which are used to verify the safety or robustness properties of the network. In case of a property is violated, the violation probability can be computed precisely by an exact verification algorithm or approximately by an overapproximate verification algorithm. The proposed approach is implemented in a tool named StarV and is evaluated using the well-known ACASXu networks and a rocket landing benchmark.","PeriodicalId":426801,"journal":{"name":"Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116858384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}