# Towards Repairing Neural Networks Correctly

arXiv: https://arxiv.org/abs/2012.01872 · HTML: https://mlsanity.com/paper/2012.01872/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 14 of 14)

- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [Verification-Aided Deep Ensemble Selection](https://mlsanity.com/paper/2202.03898/) (2022)
- [Minimal Multi-Layer Modifications of Deep Neural Networks](https://mlsanity.com/paper/2110.09929/) (2021)
- [Sound and Complete Neural Network Repair with Minimality and Locality Guarantees](https://mlsanity.com/paper/2110.07682/) (2021)
- [Verifying Generalization in Deep Learning](https://mlsanity.com/paper/2302.05745/) (2023)
- [Safe-by-Repair: A Convex Optimization Approach for Repairing Unsafe Two-Level Lattice Neural Network Controllers](https://mlsanity.com/paper/2104.02788/) (2021)
- [SpecRepair: Counter-Example Guided Safety Repair of Deep Neural Networks](https://mlsanity.com/paper/2106.01917/) (2021)
- [Local Repair of Neural Networks Using Optimization](https://mlsanity.com/paper/2109.14041/) (2021)
- [A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks](https://mlsanity.com/paper/2301.11342/) (2023)
- [DelBugV: Delta-Debugging Neural Network Verifiers](https://mlsanity.com/paper/2305.18558/) (2023)
- [A Comprehensive Study of Deep Learning Model Fixing Approaches](https://mlsanity.com/paper/2512.23745/) (2025)
- [Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics](https://mlsanity.com/paper/2405.15430/) (2024)
- [PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks](https://mlsanity.com/paper/2505.06520/) (2025)
- [Provable Repair of Deep Neural Network Defects by Preimage Synthesis and Property Refinement](https://mlsanity.com/paper/2511.07741/) (2025)

## Abstract (arXiv)

Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication). While many impressive static verification techniques have been proposed to tackle the correctness problem of neural networks, it is possible that static verification may never be sufficiently scalable to handle real-world neural networks. In this work, we propose a runtime verification method to ensure the correctness of neural networks. Given a neural network and a desirable safety property, we adopt state-of-the-art static verification techniques to identify strategically locations to introduce additional gates which "correct" neural network behaviors at runtime. Experiment results show that our approach effectively generates neural networks which are guaranteed to satisfy the properties, whilst being consistent with the original neural network most of the time.