# Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning

arXiv: https://arxiv.org/abs/2203.15506 · HTML: https://mlsanity.com/paper/2203.15506/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 52 references that are in the map.
- First posted on arXiv 25 Mar 2022.

## Builds on (most cited first, 30 of 37)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (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)
- [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)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Label-Consistent Backdoor Attacks](https://mlsanity.com/paper/1912.02771/) (2019)
- [Understanding Deep Neural Networks with Rectified Linear Units](https://mlsanity.com/paper/1611.01491/) (2016)
- [A backdoor attack against LSTM-based text classification systems](https://mlsanity.com/paper/1905.12457/) (2019)
- [Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models](https://mlsanity.com/paper/1708.08296/) (2017)
- [Detecting AI Trojans Using Meta Neural Analysis](https://mlsanity.com/paper/1910.03137/) (2019)
- [Blind Backdoors in Deep Learning Models](https://mlsanity.com/paper/2005.03823/) (2020)
- [Neural Trojans](https://mlsanity.com/paper/1710.00942/) (2017)
- [Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs](https://mlsanity.com/paper/1906.10842/) (2019)
- [Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation](https://mlsanity.com/paper/1808.10307/) (2018)
- [You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion](https://mlsanity.com/paper/2007.02220/) (2020)
- [Deep Learning in Mobile and Wireless Networking: A Survey](https://mlsanity.com/paper/1803.04311/) (2018)
- [TBT: Targeted Neural Network Attack with Bit Trojan](https://mlsanity.com/paper/1909.05193/) (2019)
- [Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy](https://mlsanity.com/paper/1911.07116/) (2019)
- [Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases](https://mlsanity.com/paper/2007.15802/) (2020)
- [Rethinking the Trigger of Backdoor Attack](https://mlsanity.com/paper/2004.04692/) (2020)
- [Backdooring Convolutional Neural Networks via Targeted Weight Perturbations](https://mlsanity.com/paper/1812.03128/) (2018)
- [Backdoor Attack against Speaker Verification](https://mlsanity.com/paper/2010.11607/) (2020)

## Built on by (most cited first, 3 of 3)

- [Circumventing interpretability: How to defeat mind-readers](https://mlsanity.com/paper/2212.11415/) (2022)
- [Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering](https://mlsanity.com/paper/2301.12318/) (2023)
- [Game of Trojans: A Submodular Byzantine Approach](https://mlsanity.com/paper/2207.05937/) (2022)

## Abstract (arXiv)

Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the neural network to misclassify the input to a (single) target class, while classifying other inputs without a trigger correctly. ML models that contain a backdoor are called Trojan models. Backdoors can have severe consequences in safety-critical cyber and cyber physical systems when only the outputs of the model are available. Defense mechanisms have been developed and illustrated to be able to distinguish between outputs from a Trojan model and a non-Trojan model in the case of a single-target backdoor attack with accuracy > 96 percent. Understanding the limitations of a defense mechanism requires the construction of examples where the mechanism fails. Current single-target backdoor attacks require one trigger per target class. We introduce a new, more general attack that will enable a single trigger to result in misclassification to more than one target class. Such a misclassification will depend on the true (actual) class that the input belongs to. We term this category of attacks multi-target backdoor attacks. We demonstrate that a Trojan model with either a single-target or multi-target trigger can be trained so that the accuracy of a defense mechanism that seeks to distinguish between outputs coming from a Trojan and a non-Trojan model will be reduced. Our approach uses the non-Trojan model as a teacher for the Trojan model and solves a min-max optimization problem between the Trojan model and defense mechanism. Empirical evaluations demonstrate that our training procedure reduces the accuracy of a state-of-the-art defense mechanism from >96 to 0 percent.