Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
From MaRDI portal
(Redirected from Publication:5033991)
Recommendations
- Robustness verification of ReLU networks via quadratic programming
- Safety Verification for Deep Neural Networks with Provable Guarantees (Invited Paper).
- Safety verification of deep neural networks
- Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio
- Generating probabilistic safety guarantees for neural network controllers
- Verisig
Cited in
(31)- Sparse polynomial optimisation for neural network verification
- Using neural networks to solve linear bilevel problems with unknown lower level
- Stability analysis of complementarity systems with neural network controllers
- Residual neural network-based observer design for continuous stirred tank reactor systems
- The Yakubovich S-Lemma Revisited: Stability and Contractivity in Non-Euclidean Norms
- Quantitative Verification for Neural Networks using ProbStars
- Verification of Recurrent Neural Networks with Star Reachability
- Robust stabilization of polytopic systems via fast and reliable neural network-based approximations
- A semi-algebraic view on quadratic constraints for polynomial systems
- Observer-based safety monitoring of nonlinear dynamical systems with neural networks via quadratic constraint approach
- Norm-induced cuts: outer approximation for Lipschitzian constraint functions
- Regular pairings for nonquadratic Lyapunov functions and contraction analysis
- Induced norm analysis of linear systems for nonnegative input signals
- Aperiodic-sampled neural network controllers with closed-loop stability verifications
- Quantitative verification of learning-enabled systems using ProbStar reachability
- Data-driven performance guarantees for classical and learned optimizers
- SAVER: a toolbox for sampling-based, probabilistic verification of neural networks
- ProbStar temporal logic for verifying complex behaviors of learning-enabled systems
- Decentralized dynamic event-triggered passive bipartite synchronization for semi-Markov jump cooperation-competition neural networks under hybrid random cyber-attacks
- Towards optimal branching of linear and semidefinite relaxations for neural network robustness certification
- Robust stability of neural network control systems with interval matrix uncertainties
- Reachability analysis of recurrent neural networks
- Quadratic maximization of reachable values of stable discrete-time affine systems
- Verifying robustness of neural networks with tight semidefinite relaxations
- LipKernel: Lipschitz-bounded convolutional neural networks via dissipative layers
- Designing neural controllers with optimality and stability guarantees by learning input-output dissipativity
- Diffusive coupling as a quadratic constraint: synchronization and stability in heterogeneous networks
- Synthesizing neural network controllers with closed-loop dissipativity guarantees
- Verification of first-order methods for parametric quadratic optimization
- LMI hierarchies for stability analysis of ReLU feedback systems
- Robustness verification of semantic segmentation neural networks using relaxed reachability
This page was built for publication: Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5033991)
