Maximal Robust Neural Network Specifications via Oracle-Guided Numerical Optimization
Abstract elided by the publisher.
Related papers
- Optimization and abstraction: a synergistic approach for analyzing neural network robustness PLDI 2019
- Exploiting Verified Neural Networks via Floating Point Numerical Error SAS 2021
- Toward Neural-Network-Guided Program Synthesis and Verification SAS 2021
- YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs CC 2024
- Improving Neural Network Verification through Spurious Region Guided Refinement TACAS 2021
- Feature-Guided Black-Box Safety Testing of Deep Neural Networks TACAS 2018
- Neural Network Robustness as a Verification Property: A Principled Case Study CAV 2022
- NNrepair: Constraint-Based Repair of Neural Network Classifiers CAV 2021