# Backdoor Mitigation in Deep Neural Networks via Strategic Retraining

arXiv: https://arxiv.org/abs/2212.07278 · HTML: https://mlsanity.com/paper/2212.07278/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 14 Dec 2022.

## Builds on (most cited first, 11 of 11)

- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [STRIP: A Defence Against Trojan Attacks on Deep Neural Networks](https://mlsanity.com/paper/1902.06531/) (2019)
- [Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks](https://mlsanity.com/paper/2007.02343/) (2020)
- [Input-Aware Dynamic Backdoor Attack](https://mlsanity.com/paper/2010.08138/) (2020)
- [Anti-Backdoor Learning: Training Clean Models on Poisoned Data](https://mlsanity.com/paper/2110.11571/) (2021)
- [Black-box Detection of Backdoor Attacks with Limited Information and Data](https://mlsanity.com/paper/2103.13127/) (2021)
- [Deep Learning for Large-Scale Traffic-Sign Detection and Recognition](https://mlsanity.com/paper/1904.00649/) (2019)
- [Neural Network Repair with Reachability Analysis](https://mlsanity.com/paper/2108.04214/) (2021)
- [Towards Dependability Metrics for Neural Networks](https://mlsanity.com/paper/1806.02338/) (2018)
- [Quantitative Projection Coverage for Testing ML-enabled Autonomous Systems](https://mlsanity.com/paper/1805.04333/) (2018)
- [Towards Safety Verification of Direct Perception Neural Networks](https://mlsanity.com/paper/1904.04706/) (2019)

## Built on by (most cited first, 1 of 1)

- [AGNES: Abstraction-guided Framework for Deep Neural Networks Security](https://mlsanity.com/paper/2311.04009/) (2023)

## Abstract (arXiv)

Deep Neural Networks (DNN) are becoming increasingly more important in assisted and automated driving. Using such entities which are obtained using machine learning is inevitable: tasks such as recognizing traffic signs cannot be developed reasonably using traditional software development methods. DNN however do have the problem that they are mostly black boxes and therefore hard to understand and debug. One particular problem is that they are prone to hidden backdoors. This means that the DNN misclassifies its input, because it considers properties that should not be decisive for the output. Backdoors may either be introduced by malicious attackers or by inappropriate training. In any case, detecting and removing them is important in the automotive area, as they might lead to safety violations with potentially severe consequences. In this paper, we introduce a novel method to remove backdoors. Our method works for both intentional as well as unintentional backdoors. We also do not require prior knowledge about the shape or distribution of backdoors. Experimental evidence shows that our method performs well on several medium-sized examples.