Robustness verification of semantic segmentation neural networks using relaxed reachability

DOI10.1007/978-3-030-81685-8_12zbMath1493.68221OpenAlexW3186627997MaRDI QIDQ832180

Neelanjana Pal, Patrick Musau, Diego Manzanas Lopez, Hoang-Dung Tran, Stanley Bak, Xiao-Dong Yang, Taylor T. Johnson, Nathaniel P. Hamilton

Publication date: 25 March 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-81685-8_12

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Specification and verification (program logics, model checking, etc.) (68Q60)

Related Items (4)

The octatope abstract domain for verification of neural networks ⋮ Quantitative Verification for Neural Networks using ProbStars ⋮ Verification of Recurrent Neural Networks with Star Reachability ⋮ Verification of piecewise deep neural networks: a star set approach with zonotope pre-filter

Uses Software

• MNIST
• Reluplex
• Marabou
• VERIFAI
• ReachNN

Cites Work

• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Verification of deep convolutional neural networks using ImageStars
• Improved geometric path enumeration for verifying ReLU neural networks
• A game-based approximate verification of deep neural networks with provable guarantees
• Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
• Verisig
• Computer vision. Algorithms and applications
• DeepSafe: a data-driven approach for assessing robustness of neural networks
• Formal specification for deep neural networks

This page was built for publication: Robustness verification of semantic segmentation neural networks using relaxed reachability