Verifying Neural Networks with Reinforcement Learning

arXiv:2609.34553 · cs.LG, cs.SE · Submitted 2026-09-28 · Read on arXiv

cs.LG, cs.SE

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)
• The Fifth International Verification of Neural Networks Competition (VNN-COMP 2024): Summary and Results
• The 6th International Verification of Neural Networks Competition (VNN-COMP 2025): Summary and Results
• Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound
• Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification
• Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers
• Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
• Neural Combinatorial Optimization with Reinforcement Learning
• Scaling Laws for Neural Language Models
• A DPLL(T) Framework for Verifying Deep Neural Networks
• Towards Deep Learning Models Resistant to Adversarial Attacks
• The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Results
• IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
• Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
• NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
• Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNs
• Proximal Policy Optimization Algorithms
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks