Set propagation techniques for reachability analysis
Reachability analysis consists in computing the set of states that are reachable by a
dynamical system from all initial states and for all admissible inputs and parameters. It is a …
dynamical system from all initial states and for all admissible inputs and parameters. It is a …
Reachability analysis for cyber-physical systems: Are we there yet?
X Chen, S Sankaranarayanan - NASA Formal Methods Symposium, 2022 - Springer
Reachability analysis is a fundamental problem in verification that checks for a given model
and set of initial states if the system will reach a given set of unsafe states. Its importance lies …
and set of initial states if the system will reach a given set of unsafe states. Its importance lies …
Reachnn: Reachability analysis of neural-network controlled systems
Applying neural networks as controllers in dynamical systems has shown great promises.
However, it is critical yet challenging to verify the safety of such control systems with neural …
However, it is critical yet challenging to verify the safety of such control systems with neural …
Reachability analysis for neural feedback systems using regressive polynomial rule inference
We present an approach to construct reachable set overapproximations for continuous-time
dynamical systems controlled using neural network feedback systems. Feedforward deep …
dynamical systems controlled using neural network feedback systems. Feedforward deep …
Polar: A polynomial arithmetic framework for verifying neural-network controlled systems
We present POLAR (The source code can be found at https://github. com/ChaoHuang2018/
POLAR_Tool. The full version of this paper can be found at https://arxiv …
POLAR_Tool. The full version of this paper can be found at https://arxiv …
Real-time attack-recovery for cyber-physical systems using linear approximations
Attack detection and recovery are fundamental elements for the operation of safe and
resilient cyber-physical systems. Most of the literature focuses on attack-detection, while …
resilient cyber-physical systems. Most of the literature focuses on attack-detection, while …
Reachability analysis and safety verification for neural network control systems
W Xiang, TT Johnson - arXiv preprint arXiv:1805.09944, 2018 - arxiv.org
Autonomous cyber-physical systems (CPS) rely on the correct operation of numerous
components, with state-of-the-art methods relying on machine learning (ML) and artificial …
components, with state-of-the-art methods relying on machine learning (ML) and artificial …
Polar-express: Efficient and precise formal reachability analysis of neural-network controlled systems
Neural networks (NNs) playing the role of controllers have demonstrated impressive
empirical performance on challenging control problems. However, the potential adoption of …
empirical performance on challenging control problems. However, the potential adoption of …
Reach set approximation through decomposition with low-dimensional sets and high-dimensional matrices
Approximating the set of reachable states of a dynamical system is an algorithmic yet
mathematically rigorous way to reason about its safety. Although progress has been made in …
mathematically rigorous way to reason about its safety. Although progress has been made in …
Predictive runtime monitoring of vehicle models using Bayesian estimation and reachability analysis
We present a predictive runtime monitoring technique for estimating future vehicle positions
and the probability of collisions with obstacles. Vehicle dynamics model how the position …
and the probability of collisions with obstacles. Vehicle dynamics model how the position …