Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming

DOI10.1109/TAC.2020.3046193OpenAlexW3117881175MaRDI QIDQ5033991

Manfred Morari, Mahyar Fazlyab, George J. Pappas

Publication date: 24 February 2022

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1903.01287

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Related Items

Robustness verification of semantic segmentation neural networks using relaxed reachability ⋮ 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