Falsification of cyber-physical systems using deep reinforcement learning
T Akazaki, S Liu, Y Yamagata, Y Duan… - … , FM 2018, Held as Part of …, 2018 - Springer
With the rapid development of software and distributed computing, Cyber-Physical Systems
(CPS) are widely adopted in many application areas, eg, smart grid, autonomous …
(CPS) are widely adopted in many application areas, eg, smart grid, autonomous …
Falsification of cyber-physical systems using deep reinforcement learning
Y Yamagata, S Liu, T Akazaki… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
A Cyber-Physical System (CPS) is a system which consists of software components and
physical components. Traditional system verification techniques such as model checking or …
physical components. Traditional system verification techniques such as model checking or …
Falsification of cyber-physical systems with robustness-guided black-box checking
M Waga - Proceedings of the 23rd International Conference on …, 2020 - dl.acm.org
For exhaustive formal verification, industrial-scale cyber-physical systems (CPSs) are often
too large and complex, and lightweight alternatives (eg, monitoring and testing) have …
too large and complex, and lightweight alternatives (eg, monitoring and testing) have …
Compositional falsification of cyber-physical systems with machine learning components
Abstract Cyber-physical systems (CPS), such as automotive systems, are starting to include
sophisticated machine learning (ML) components. Their correctness, therefore, depends on …
sophisticated machine learning (ML) components. Their correctness, therefore, depends on …
An active learning approach to the falsification of black box cyber-physical systems
S Silvetti, A Policriti, L Bortolussi - … , IFM 2017, Turin, Italy, September 20-22 …, 2017 - Springer
Search-based testing is widely used to find bugs in models of complex Cyber-Physical
Systems. Latest research efforts have improved this approach by casting it as a falsification …
Systems. Latest research efforts have improved this approach by casting it as a falsification …
Effective hybrid system falsification using Monte Carlo tree search guided by QB-robustness
Hybrid system falsification is an important quality assurance method for cyber-physical
systems with the advantage of scalability and feasibility in practice than exhaustive …
systems with the advantage of scalability and feasibility in practice than exhaustive …
Efficient optimization-based falsification of cyber-physical systems with multiple conjunctive requirements
L Mathesen, G Pedrielli… - 2021 IEEE 17th …, 2021 - ieeexplore.ieee.org
Optimization-based falsification, or search-based testing, is a method of automatic test
generation for Cyber-Physical System (CPS) safety evaluation. CPS safety evaluation is …
generation for Cyber-Physical System (CPS) safety evaluation. CPS safety evaluation is …
[PDF][PDF] Towards scalable verification of deep reinforcement learning
Deep neural networks (DNNs) have gained significant popularity in recent years, becoming
the state of the art in a variety of domains. In particular, deep reinforcement learning (DRL) …
the state of the art in a variety of domains. In particular, deep reinforcement learning (DRL) …
Verifying deep-RL-driven systems
Deep reinforcement learning (RL) has recently been successfully applied to networking
contexts including routing, flow scheduling, congestion control, packet classification, cloud …
contexts including routing, flow scheduling, congestion control, packet classification, cloud …
FIGCPS: Effective failure-inducing input generation for cyber-physical systems with deep reinforcement learning
Cyber-Physical Systems (CPSs) are composed of computational control logic and physical
processes, which intertwine with each other. CPSs are widely used in various domains of …
processes, which intertwine with each other. CPSs are widely used in various domains of …