# A Perturbation Resistant Transformation and Classification System for Deep Neural Networks

arXiv: https://arxiv.org/abs/2208.11839 · HTML: https://mlsanity.com/paper/2208.11839/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 25 Aug 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Countering Adversarial Images using Input Transformations](https://mlsanity.com/paper/1711.00117/) (2017)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Mitigating Adversarial Effects Through Randomization](https://mlsanity.com/paper/1711.01991/) (2017)
- [PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples](https://mlsanity.com/paper/1710.10766/) (2017)
- [MMA Training: Direct Input Space Margin Maximization through Adversarial Training](https://mlsanity.com/paper/1812.02637/) (2018)
- [Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training](https://mlsanity.com/paper/1907.10764/) (2019)
- [Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression](https://mlsanity.com/paper/1802.06816/) (2018)
- [Image Super-Resolution as a Defense Against Adversarial Attacks](https://mlsanity.com/paper/1901.01677/) (2019)
- [APE-GAN: Adversarial Perturbation Elimination with GAN](https://mlsanity.com/paper/1707.05474/) (2017)
- [Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks](https://mlsanity.com/paper/1904.00887/) (2019)
- [MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples](https://mlsanity.com/paper/1711.08478/) (2017)
- [Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong](https://mlsanity.com/paper/1706.04701/) (2017)
- [Robustness to Adversarial Examples through an Ensemble of Specialists](https://mlsanity.com/paper/1702.06856/) (2017)
- [Cascade Adversarial Machine Learning Regularized with a Unified Embedding](https://mlsanity.com/paper/1708.02582/) (2017)
- [Stylized Adversarial Defense](https://mlsanity.com/paper/2007.14672/) (2020)

## Abstract (arXiv)

Deep convolutional neural networks accurately classify a diverse range of natural images, but may be easily deceived when designed, imperceptible perturbations are embedded in the images. In this paper, we design a multi-pronged training, input transformation, and image ensemble system that is attack agnostic and not easily estimated. Our system incorporates two novel features. The first is a transformation layer that computes feature level polynomial kernels from class-level training data samples and iteratively updates input image copies at inference time based on their feature kernel differences to create an ensemble of transformed inputs. The second is a classification system that incorporates the prediction of the undefended network with a hard vote on the ensemble of filtered images. Our evaluations on the CIFAR10 dataset show our system improves the robustness of an undefended network against a variety of bounded and unbounded white-box attacks under different distance metrics, while sacrificing little accuracy on clean images. Against adaptive full-knowledge attackers creating end-to-end attacks, our system successfully augments the existing robustness of adversarially trained networks, for which our methods are most effectively applied.