Exploring Solver-Level Warmstarting for Neural Network Verification
cs.LG
Submitted: 2026-09-22
Updated: 2026-09-22
Comments: to be published in the postproceedings of WORKSHOP ON SECURE AND TRUSTWORTHY AI (2026) co-located with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Code: https://github.com/ADA-research/STAI-Solver-Level-Warmstarting-paper
License: http://creativecommons.org/licenses/by/4.0/
The gist: Neural network verification has become a key tool for providing formal guarantees on the behaviour of neural networks.
Terminology
Abstract
Neural network verification has become a key tool for providing formal guarantees on the behaviour of neural networks. However, many verification problems remain computationally intractable in the worst case: even for common adversarial robustness specifications, verification is NP-complete. Here, we explore the application of solver-level warmstarting for neural network verification to exploit information from previous solutions. We study the effect on running time as several properties are modified, including perturbation radii, input data and the networks themselves, using a pipeline that is generalisable and potentially adaptable to state-of-the-art verifiers. Our results show that warmstarting can significantly reduce verification time in most cases. Moreover, warmstarting enables the successful verification of instances that could not be solved from scratch within the given time limit.
Sources
- Relational DNN Verification With Cross Executional Bound Refinement
- Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
- Incremental Neural Network Verification via Learned Conflicts
- Delving into Transferable Adversarial Examples and Black-box Attacks
- Intriguing properties of neural networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks