mlsanityData to 7 Oct 2026

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

arXiv 2202.10582 ↗First posted 18 Feb 2022cs.CR cs.AI cs.LGcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 41 references that are in the map. First posted on arXiv 18 Feb 2022.

Builds on

23 of 41 references.

References · 23

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  3. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  4. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  5. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
  6. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
  7. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  8. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 426
  9. 2020Backdoor Learning: A Surveycited by 412
  10. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  11. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  12. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
11 more
  1. 2020Entangled Watermarks as a Defense against Model Extractioncited by 144
  2. 2021Fair Mixup: Fairness via Interpolationcited by 109
  3. 2020An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networkscited by 92
  4. 2018Achieving Fairness through Adversarial Learning: an Application to Recidivism Predictioncited by 77
  5. 2019Interpreting Adversarially Trained Convolutional Neural Networkscited by 75
  6. 2021Fairness via Representation Neutralizationcited by 63
  7. 2021Fair Feature Distillation for Visual Recognitioncited by 59
  8. 2018Fairness GANcited by 32
  9. 2020Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasingcited by 32
  10. 2018Replication study: Development and validation of deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographscited by 17
  11. 2020Adversarial Privacy-preserving Filtercited by 13

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024MADE: Graph Backdoor Defense with Masked Unlearningcited by 1