# Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias

arXiv: https://arxiv.org/abs/2202.10582 · HTML: https://mlsanity.com/paper/2202.10582/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 18 Feb 2022.

## Builds on (most cited first, 23 of 23)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [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)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Backdoor Learning: A Survey](https://mlsanity.com/paper/2007.08745/) (2020)
- [Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring](https://mlsanity.com/paper/1802.04633/) (2018)
- [Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks](https://mlsanity.com/paper/2007.02343/) (2020)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Entangled Watermarks as a Defense against Model Extraction](https://mlsanity.com/paper/2002.12200/) (2020)
- [Fair Mixup: Fairness via Interpolation](https://mlsanity.com/paper/2103.06503/) (2021)
- [An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks](https://mlsanity.com/paper/2006.08131/) (2020)
- [Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction](https://mlsanity.com/paper/1807.00199/) (2018)
- [Interpreting Adversarially Trained Convolutional Neural Networks](https://mlsanity.com/paper/1905.09797/) (2019)
- [Fairness via Representation Neutralization](https://mlsanity.com/paper/2106.12674/) (2021)
- [Fair Feature Distillation for Visual Recognition](https://mlsanity.com/paper/2106.04411/) (2021)
- [Fairness GAN](https://mlsanity.com/paper/1805.09910/) (2018)
- [Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing](https://mlsanity.com/paper/2007.13632/) (2020)
- [Replication study: Development and validation of deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs](https://mlsanity.com/paper/1803.04337/) (2018)
- [Adversarial Privacy-preserving Filter](https://mlsanity.com/paper/2007.12861/) (2020)

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

- [MADE: Graph Backdoor Defense with Masked Unlearning](https://mlsanity.com/paper/2411.18648/) (2024)

## Abstract (arXiv)

Backdoor attack is a new AI security risk that has emerged in recent years. Drawing on the previous research of adversarial attack, we argue that the backdoor attack has the potential to tap into the model learning process and improve model performance. Based on Clean Accuracy Drop (CAD) in backdoor attack, we found that CAD came out of the effect of pseudo-deletion of data. We provided a preliminary explanation of this phenomenon from the perspective of model classification boundaries and observed that this pseudo-deletion had advantages over direct deletion in the data debiasing problem. Based on the above findings, we proposed Debiasing Backdoor Attack (DBA). It achieves SOTA in the debiasing task and has a broader application scenario than undersampling.