# Universal Soldier: Using Universal Adversarial Perturbations for Detecting Backdoor Attacks

arXiv: https://arxiv.org/abs/2302.00747 · HTML: https://mlsanity.com/paper/2302.00747/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 1 Feb 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (2018)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [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)
- [Certified Defenses for Data Poisoning Attacks](https://mlsanity.com/paper/1706.03691/) (2017)
- [Label-Consistent Backdoor Attacks](https://mlsanity.com/paper/1912.02771/) (2019)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [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)
- [Clean-Label Backdoor Attacks on Video Recognition Models](https://mlsanity.com/paper/2003.03030/) (2020)
- [Neural Trojans](https://mlsanity.com/paper/1710.00942/) (2017)
- [Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation](https://mlsanity.com/paper/1808.10307/) (2018)
- [Certified Robustness to Label-Flipping Attacks via Randomized Smoothing](https://mlsanity.com/paper/2002.03018/) (2020)
- [Data Poisoning against Differentially-Private Learners: Attacks and Defenses](https://mlsanity.com/paper/1903.09860/) (2019)
- [Bypassing Backdoor Detection Algorithms in Deep Learning](https://mlsanity.com/paper/1905.13409/) (2019)
- [Black-box Detection of Backdoor Attacks with Limited Information and Data](https://mlsanity.com/paper/2103.13127/) (2021)
- [TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors](https://mlsanity.com/paper/2012.09302/) (2020)
- [RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN](https://mlsanity.com/paper/2208.10608/) (2022)

## Built on by (most cited first, 2 of 2)

- [BAN: Detecting Backdoors Activated by Adversarial Neuron Noise](https://mlsanity.com/paper/2405.19928/) (2024)
- [Clean-image Backdoor Attacks](https://mlsanity.com/paper/2403.15010/) (2024)

## Abstract (arXiv)

Deep learning models achieve excellent performance in numerous machine learning tasks. Yet, they suffer from security-related issues such as adversarial examples and poisoning (backdoor) attacks. A deep learning model may be poisoned by training with backdoored data or by modifying inner network parameters. Then, a backdoored model performs as expected when receiving a clean input, but it misclassifies when receiving a backdoored input stamped with a pre-designed pattern called "trigger". Unfortunately, it is difficult to distinguish between clean and backdoored models without prior knowledge of the trigger. This paper proposes a backdoor detection method by utilizing a special type of adversarial attack, universal adversarial perturbation (UAP), and its similarities with a backdoor trigger. We observe an intuitive phenomenon: UAPs generated from backdoored models need fewer perturbations to mislead the model than UAPs from clean models. UAPs of backdoored models tend to exploit the shortcut from all classes to the target class, built by the backdoor trigger. We propose a novel method called Universal Soldier for Backdoor detection (USB) and reverse engineering potential backdoor triggers via UAPs. Experiments on 345 models trained on several datasets show that USB effectively detects the injected backdoor and provides comparable or better results than state-of-the-art methods.