# On the Effectiveness of Adversarial Training against Backdoor Attacks

arXiv: https://arxiv.org/abs/2202.10627 · HTML: https://mlsanity.com/paper/2202.10627/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 56 references that are in the map.
- First posted on arXiv 22 Feb 2022.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [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)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [Backdoor Learning: A Survey](https://mlsanity.com/paper/2007.08745/) (2020)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Do Adversarially Robust ImageNet Models Transfer Better?](https://mlsanity.com/paper/2007.08489/) (2020)
- [Label-Consistent Backdoor Attacks](https://mlsanity.com/paper/1912.02771/) (2019)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Anti-Backdoor Learning: Training Clean Models on Poisoned Data](https://mlsanity.com/paper/2110.11571/) (2021)
- [Attacks Which Do Not Kill Training Make Adversarial Learning Stronger](https://mlsanity.com/paper/2002.11242/) (2020)
- [A new Backdoor Attack in CNNs by training set corruption without label poisoning](https://mlsanity.com/paper/1902.11237/) (2019)
- [Adversarial Neuron Pruning Purifies Backdoored Deep Models](https://mlsanity.com/paper/2110.14430/) (2021)
- [Bag of Tricks for Adversarial Training](https://mlsanity.com/paper/2010.00467/) (2020)
- [Geometry-aware Instance-reweighted Adversarial Training](https://mlsanity.com/paper/2010.01736/) (2020)
- [Spatially Transformed Adversarial Examples](https://mlsanity.com/paper/1801.02612/) (2018)
- [Adversarial Training and Robustness for Multiple Perturbations](https://mlsanity.com/paper/1904.13000/) (2019)
- [Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses](https://mlsanity.com/paper/2012.10544/) (2020)
- [Adversarial Unlearning of Backdoors via Implicit Hypergradient](https://mlsanity.com/paper/2110.03735/) (2021)
- [Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching](https://mlsanity.com/paper/2009.02276/) (2020)
- [Poisoning and Backdooring Contrastive Learning](https://mlsanity.com/paper/2106.09667/) (2021)

## Built on by (most cited first, 16 of 16)

- [Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples](https://mlsanity.com/paper/2307.10562/) (2023)
- [CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization](https://mlsanity.com/paper/2411.12768/) (2024)
- [Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey](https://mlsanity.com/paper/2410.23687/) (2024)
- [Defenses in Adversarial Machine Learning: A Survey](https://mlsanity.com/paper/2312.08890/) (2023)
- [Backdoor Vulnerabilities in Normally Trained Deep Learning Models](https://mlsanity.com/paper/2211.15929/) (2022)
- [RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model](https://mlsanity.com/paper/2206.00700/) (2022)
- [Towards Unified Robustness Against Both Backdoor and Adversarial Attacks](https://mlsanity.com/paper/2405.17929/) (2024)
- [Adversarial Backdoor Defense in CLIP](https://mlsanity.com/paper/2409.15968/) (2024)
- [Adversarial Training: A Survey](https://mlsanity.com/paper/2410.15042/) (2024)
- [Universal Detection of Backdoor Attacks via Density-based Clustering and Centroids Analysis](https://mlsanity.com/paper/2301.04554/) (2023)
- [DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning](https://mlsanity.com/paper/2411.12220/) (2024)
- [Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning](https://mlsanity.com/paper/2310.11594/) (2023)
- [BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models](https://mlsanity.com/paper/2605.12529/) (2026)
- [From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging](https://mlsanity.com/paper/2606.12498/) (2026)
- [NT-ML: Backdoor Defense via Non-target Label Training and Mutual Learning](https://mlsanity.com/paper/2508.05404/) (2025)
- [Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learning](https://mlsanity.com/paper/2606.14078/) (2026)

## Abstract (arXiv)

DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in the presence of a predefined trigger pattern, which can be easily realized via poisoning a small amount of data. In general, adversarial training is believed to defend against backdoor attacks since it helps models to keep their prediction unchanged even if we perturb the input image (as long as within a feasible range). Unfortunately, few previous studies succeed in doing so. To explore whether adversarial training could defend against backdoor attacks or not, we conduct extensive experiments across different threat models and perturbation budgets, and find the threat model in adversarial training matters. For instance, adversarial training with spatial adversarial examples provides notable robustness against commonly-used patch-based backdoor attacks. We further propose a hybrid strategy which provides satisfactory robustness across different backdoor attacks.