# Repairing Deep Neural Networks Based on Behavior Imitation

arXiv: https://arxiv.org/abs/2305.03365 · HTML: https://mlsanity.com/paper/2305.03365/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 58 references that are in the map.
- First posted on arXiv 5 May 2023.

## Builds on (most cited first, 30 of 30)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks](https://mlsanity.com/paper/1702.01135/) (2017)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models](https://mlsanity.com/paper/1810.12715/) (2018)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Editable Neural Networks](https://mlsanity.com/paper/2004.00345/) (2020)
- [Panoptic 3D Scene Reconstruction From a Single RGB Image](https://mlsanity.com/paper/2111.02444/) (2021)
- [Deep Neural Network Compression for Aircraft Collision Avoidance Systems](https://mlsanity.com/paper/1810.04240/) (2018)
- [An SMT-Based Approach for Verifying Binarized Neural Networks](https://mlsanity.com/paper/2011.02948/) (2020)
- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [Provable Repair of Deep Neural Networks](https://mlsanity.com/paper/2104.04413/) (2021)
- [POPQORN: Quantifying Robustness of Recurrent Neural Networks](https://mlsanity.com/paper/1905.07387/) (2019)
- [Neural Network Robustness as a Verification Property: A Principled Case Study](https://mlsanity.com/paper/2104.01396/) (2021)
- [Improving Neural Network Verification through Spurious Region Guided Refinement](https://mlsanity.com/paper/2010.07722/) (2020)
- [DeepFault: Fault Localization for Deep Neural Networks](https://mlsanity.com/paper/1902.05974/) (2019)
- [ReachNN: Reachability Analysis of Neural-Network Controlled Systems](https://mlsanity.com/paper/1906.10654/) (2019)
- [Arachne: Search Based Repair of Deep Neural Networks](https://mlsanity.com/paper/1912.12463/) (2019)
- [Towards Characterizing Adversarial Defects of Deep Learning Software from the Lens of Uncertainty](https://mlsanity.com/paper/2004.11573/) (2020)
- [NNrepair: Constraint-based Repair of Neural Network Classifiers](https://mlsanity.com/paper/2103.12535/) (2021)
- [Neural Network Repair with Reachability Analysis](https://mlsanity.com/paper/2108.04214/) (2021)
- [Probabilistic Verification of Neural Networks Against Group Fairness](https://mlsanity.com/paper/2107.08362/) (2021)
- [ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks](https://mlsanity.com/paper/1907.10662/) (2019)
- [Towards Practical Robustness Analysis for DNNs based on PAC-Model Learning](https://mlsanity.com/paper/2101.10102/) (2021)
- [SOCRATES: Towards a Unified Platform for Neural Network Analysis](https://mlsanity.com/paper/2007.11206/) (2020)
- [Grounding Spatio-Temporal Language with Transformers](https://mlsanity.com/paper/2106.08858/) (2021)
- [Safety Verification for Neural Networks Based on Set-boundary Analysis](https://mlsanity.com/paper/2210.04175/) (2022)
- [Local Repair of Neural Networks Using Optimization](https://mlsanity.com/paper/2109.14041/) (2021)
- [Optimization assisted MCMC](https://mlsanity.com/paper/1709.02888/) (2017)
- [A Comprehensive Study on Challenges in Deploying Deep Learning Based Software](https://mlsanity.com/paper/2005.00760/) (2020)

## Built on by (most cited first, 4 of 4)

- [A Survey on Knowledge Editing of Neural Networks](https://mlsanity.com/paper/2310.19704/) (2023)
- [A Survey of Imitation Learning Methods, Environments and Metrics](https://mlsanity.com/paper/2404.19456/) (2024)
- [Path Analysis for Effective Fault Localization in Deep Neural Networks](https://mlsanity.com/paper/2310.18987/) (2023)
- [DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis](https://mlsanity.com/paper/2509.26562/) (2025)

## Abstract (arXiv)

The increasing use of deep neural networks (DNNs) in safety-critical systems has raised concerns about their potential for exhibiting ill-behaviors. While DNN verification and testing provide post hoc conclusions regarding unexpected behaviors, they do not prevent the erroneous behaviors from occurring. To address this issue, DNN repair/patch aims to eliminate unexpected predictions generated by defective DNNs. Two typical DNN repair paradigms are retraining and fine-tuning. However, existing methods focus on the high-level abstract interpretation or inference of state spaces, ignoring the underlying neurons' outputs. This renders patch processes computationally prohibitive and limited to piecewise linear (PWL) activation functions to great extent. To address these shortcomings, we propose a behavior-imitation based repair framework, BIRDNN, which integrates the two repair paradigms for the first time. BIRDNN corrects incorrect predictions of negative samples by imitating the closest expected behaviors of positive samples during the retraining repair procedure. For the fine-tuning repair process, BIRDNN analyzes the behavior differences of neurons on positive and negative samples to identify the most responsible neurons for the erroneous behaviors. To tackle more challenging domain-wise repair problems (DRPs), we synthesize BIRDNN with a domain behavior characterization technique to repair buggy DNNs in a probably approximated correct style. We also implement a prototype tool based on BIRDNN and evaluate it on ACAS Xu DNNs. Our experimental results show that BIRDNN can successfully repair buggy DNNs with significantly higher efficiency than state-of-the-art repair tools. Additionally, BIRDNN is highly compatible with different activation functions.