# Arachne: Search Based Repair of Deep Neural Networks

arXiv: https://arxiv.org/abs/1912.12463 · HTML: https://mlsanity.com/paper/1912.12463/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2019.

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

- [Machine Learning Robustness: A Primer](https://mlsanity.com/paper/2404.00897/) (2024)
- [Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation](https://mlsanity.com/paper/2312.05356/) (2023)
- [AIREPAIR: A Repair Platform for Neural Networks](https://mlsanity.com/paper/2211.15387/) (2022)
- [Repairing Deep Neural Networks Based on Behavior Imitation](https://mlsanity.com/paper/2305.03365/) (2023)
- [LUNA: A Model-Based Universal Analysis Framework for Large Language Models](https://mlsanity.com/paper/2310.14211/) (2023)
- [FAST: Boosting Uncertainty-based Test Prioritization Methods for Neural Networks via Feature Selection](https://mlsanity.com/paper/2409.09130/) (2024)
- [DNN Modularization via Activation-Driven Training](https://mlsanity.com/paper/2411.01074/) (2024)
- [COSMosFL: Ensemble of Small Language Models for Fault Localisation](https://mlsanity.com/paper/2502.02908/) (2025)
- [A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation](https://mlsanity.com/paper/2503.12899/) (2025)
- [Feature-Guided Analysis of Neural Networks: A Replication Study](https://mlsanity.com/paper/2511.00052/) (2025)
- [A Comprehensive Study of Deep Learning Model Fixing Approaches](https://mlsanity.com/paper/2512.23745/) (2025)
- [One-Shot Domain Incremental Learning](https://mlsanity.com/paper/2403.16707/) (2024)
- [On Accelerating Deep Neural Network Mutation Analysis by Neuron and Mutant Clustering](https://mlsanity.com/paper/2501.12598/) (2025)
- [An Experience Report on Regression-Free Repair of Deep Neural Network Model](https://mlsanity.com/paper/2503.07079/) (2025)
- [Hazards in Deep Learning Testing: Prevalence, Impact and Recommendations](https://mlsanity.com/paper/2309.05381/) (2023)
- [Path Analysis for Effective Fault Localization in Deep Neural Networks](https://mlsanity.com/paper/2310.18987/) (2023)
- [Patch Synthesis for Property Repair of Deep Neural Networks](https://mlsanity.com/paper/2404.01642/) (2024)
- [An Empirical Study of Fault Localisation Techniques for Deep Learning](https://mlsanity.com/paper/2412.11304/) (2024)
- [Causality-Driven Neural Network Repair: Challenges and Opportunities](https://mlsanity.com/paper/2504.17946/) (2025)
- [PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks](https://mlsanity.com/paper/2505.06520/) (2025)
- [Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap](https://mlsanity.com/paper/2505.19625/) (2025)
- [FairFLRep: Fairness aware fault localization and repair of Deep Neural Networks](https://mlsanity.com/paper/2508.08151/) (2025)
- [DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis](https://mlsanity.com/paper/2509.26562/) (2025)
- [Provable Repair of Deep Neural Network Defects by Preimage Synthesis and Property Refinement](https://mlsanity.com/paper/2511.07741/) (2025)
- [Provable Fairness Repair for Deep Neural Networks](https://mlsanity.com/paper/2605.19549/) (2026)
- [RepTran: Search-Based Repair of Transformer Models](https://mlsanity.com/paper/2607.11193/) (2026)

## Abstract (arXiv)

The rapid and widespread adoption of Deep Neural Networks (DNNs) has called for ways to test their behaviour, and many testing approaches have successfully revealed misbehaviour of DNNs. However, it is relatively unclear what one can do to correct such behaviour after revelation, as retraining involves costly data collection and does not guarantee to fix the underlying issue. This paper introduces Arachne, a novel program repair technique for DNNs, which directly repairs DNNs using their input-output pairs as a specification. Arachne localises neural weights on which it can generate effective patches and uses Differential Evolution to optimise the localised weights and correct the misbehaviour. An empirical study using different benchmarks shows that Arachne can fix specific misclassifications of a DNN without reducing general accuracy significantly. On average, patches generated by Arachne generalise to 61.3% of unseen misbehaviour, whereas those by a state-of-the-art DNN repair technique generalise only to 10.2% and sometimes to none while taking tens of times more than Arachne. We also show that Arachne can address fairness issues by debiasing a gender classification model. Finally, we successfully apply Arachne to a text sentiment model to show that it generalises beyond Convolutional Neural Networks.