# NNrepair: Constraint-based Repair of Neural Network Classifiers

arXiv: https://arxiv.org/abs/2103.12535 · HTML: https://mlsanity.com/paper/2103.12535/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 23 Mar 2021.

## Builds on (most cited first, 7 of 7)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Provable defenses against adversarial examples via the convex outer adversarial polytope](https://mlsanity.com/paper/1711.00851/) (2017)
- [Repairing Deep Neural Networks: Fix Patterns and Challenges](https://mlsanity.com/paper/2005.00972/) (2020)
- [DeepFault: Fault Localization for Deep Neural Networks](https://mlsanity.com/paper/1902.05974/) (2019)
- [Automatic Software Repair: a Bibliography](https://mlsanity.com/paper/1807.00515/) (2018)
- [NEUROSPF: A tool for the Symbolic Analysis of Neural Networks](https://mlsanity.com/paper/2103.00124/) (2021)

## Built on by (most cited first, 26 of 26)

- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [An Abstraction-Refinement Approach to Verifying Convolutional Neural Networks](https://mlsanity.com/paper/2201.01978/) (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)
- [Verifying Generalization in Deep Learning](https://mlsanity.com/paper/2302.05745/) (2023)
- [Architecture-Preserving Provable Repair of Deep Neural Networks](https://mlsanity.com/paper/2304.03496/) (2023)
- [SpecRepair: Counter-Example Guided Safety Repair of Deep Neural Networks](https://mlsanity.com/paper/2106.01917/) (2021)
- [Repairing Deep Neural Networks Based on Behavior Imitation](https://mlsanity.com/paper/2305.03365/) (2023)
- [Safe and Reliable Training of Learning-Based Aerospace Controllers](https://mlsanity.com/paper/2407.07088/) (2024)
- [DelBugV: Delta-Debugging Neural Network Verifiers](https://mlsanity.com/paper/2305.18558/) (2023)
- [Semantic-Based Neural Network Repair](https://mlsanity.com/paper/2306.07995/) (2023)
- [CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models](https://mlsanity.com/paper/2405.07668/) (2024)
- [VPN: Verification of Poisoning in Neural Networks](https://mlsanity.com/paper/2205.03894/) (2022)
- [Incremental Satisfiability Modulo Theory for Verification of Deep Neural Networks](https://mlsanity.com/paper/2302.06455/) (2023)
- [Prophecy: Inferring Formal Properties from Neuron Activations](https://mlsanity.com/paper/2509.21677/) (2025)
- [A Comprehensive Study of Deep Learning Model Fixing Approaches](https://mlsanity.com/paper/2512.23745/) (2025)
- [TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance](https://mlsanity.com/paper/2312.13632/) (2023)
- [Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment](https://mlsanity.com/paper/2401.14628/) (2024)
- [Kill it with FIRE: On Leveraging Latent Space Directions for Runtime Backdoor Mitigation in Deep Neural Networks](https://mlsanity.com/paper/2602.10780/) (2026)
- [WARP: Guaranteed Inner-Layer Repair of NLP Transformers](https://mlsanity.com/paper/2604.00938/) (2026)
- [QNNRepair: Quantized Neural Network Repair](https://mlsanity.com/paper/2306.13793/) (2023)
- [Path Analysis for Effective Fault Localization in Deep Neural Networks](https://mlsanity.com/paper/2310.18987/) (2023)
- [Inferring Properties of Graph Neural Networks](https://mlsanity.com/paper/2401.03790/) (2024)
- [Shapley-Guided Neural Repair Approach via Derivative-Free Optimization](https://mlsanity.com/paper/2604.00422/) (2026)
- [FORGE: Verification-Gated Behavioral Repair for Generative Language Models](https://mlsanity.com/paper/2610.05190/) (2026)
- [Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models](https://mlsanity.com/paper/2610.05277/) (2026)

## Abstract (arXiv)

We present NNrepair, a constraint-based technique for repairing neural network classifiers. The technique aims to fix the logic of the network at an intermediate layer or at the last layer. NNrepair first uses fault localization to find potentially faulty network parameters (such as the weights) and then performs repair using constraint solving to apply small modifications to the parameters to remedy the defects. We present novel strategies to enable precise yet efficient repair such as inferring correctness specifications to act as oracles for intermediate layer repair, and generation of experts for each class. We demonstrate the technique in the context of three different scenarios: (1) Improving the overall accuracy of a model, (2) Fixing security vulnerabilities caused by poisoning of training data and (3) Improving the robustness of the network against adversarial attacks. Our evaluation on MNIST and CIFAR-10 models shows that NNrepair can improve the accuracy by 45.56 percentage points on poisoned data and 10.40 percentage points on adversarial data. NNrepair also provides small improvement in the overall accuracy of models, without requiring new data or re-training.