Abstract Interpretation of ReLU Neural Networks with Optimizable Polynomial Relaxations
Abstract elided by the publisher.
Related papers
- Static Analysis of ReLU Neural Networks with Tropical Polyhedra SAS 2021
- PEREGRiNN: Penalized-Relaxation Greedy Neural Network Verifier CAV 2021
- Robustness Verification of Semantic Segmentation Neural Networks Using Relaxed Reachability CAV 2021
- Provable Preimage Under-Approximation for Neural Networks TACAS 2024
- PRIMA: general and precise neural network certification via scalable convex hull approximations POPL 2022
- Precise Verification of Transformers Through ReLU-Catalyzed Abstraction Refinement CAV 2026
- Improved Geometric Path Enumeration for Verifying ReLU Neural Networks CAV 2020
- Abstract Neural Networks SAS 2020