mlsanityData to 7 Oct 2026

NT-ML: Backdoor Defense via Non-target Label Training and Mutual Learning

arXiv 2508.05404 ↗First posted 7 Aug 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense mechanism, Non-target label Training and Mutual Learning (NT-ML), which can successfully restore the poisoned model under advanced backdoor attacks. NT aims to reduce the harm of poisoned data by retraining the model with the outputs of the standard training. At this stage, a teacher model with high accuracy on clean data and a student model with higher confidence in correct prediction on poisoned data are obtained. Then, the teacher and student can learn the strengths from each other through ML to obtain a purified student model. Extensive experiments show that NT-ML can effectively defend against 6 backdoor attacks with a small number of clean samples, and outperforms 5 state-of-the-art backdoor defenses.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 47 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

37 of 47 references.

References · 37

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  5. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  6. 2020Knowledge Distillation: A Surveycited by 1,578
  7. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  8. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  9. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  10. 2017Deep Mutual Learningcited by 621
  11. 2019Improved Knowledge Distillation via Teacher Assistantcited by 567
  12. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
25 more
  1. 2019Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillationcited by 491
  2. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  3. 2020Backdoor Learning: A Surveycited by 412
  4. 2022Decoupled Knowledge Distillationcited by 380
  5. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  6. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 338
  7. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 313
  8. 2019Label-Consistent Backdoor Attackscited by 285
  9. 2019Correlation Congruence for Knowledge Distillationcited by 280
  10. 2019A new Backdoor Attack in CNNs by training set corruption without label poisoningcited by 237
  11. 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 230
  12. 2019Learning Lightweight Lane Detection CNNs by Self Attention Distillationcited by 162
  13. 2022Backdoor Defense via Decoupling the Training Processcited by 149
  14. 2022Narcissus: A Practical Clean-Label Backdoor Attack with Limited Informationcited by 102
  15. 2018Snapshot Distillation: Teacher-Student Optimization in One Generationcited by 99
  16. 2022BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learningcited by 82
  17. 2018Label Refinery: Improving ImageNet Classification through Label Progressioncited by 65
  18. 2023Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimizationcited by 60
  19. 2019Model Agnostic Defence against Backdoor Attacks in Machine Learningcited by 52
  20. 2023Backdoor Defense via Adaptively Splitting Poisoned Datasetcited by 43
  21. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 41
  22. 2021Few-shot Backdoor Defense Using Shapley Estimationcited by 40
  23. 2022Backdoor Cleansing with Unlabeled Datacited by 17
  24. 2022On the Effectiveness of Adversarial Training against Backdoor Attackscited by 15
  25. 2023Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNscited by 8

Built on by

Not cited yet.