# Machine Beats Machine: Machine Learning Models to Defend Against Adversarial Attacks

arXiv: https://arxiv.org/abs/2209.13963 · HTML: https://mlsanity.com/paper/2209.13963/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 28 Sep 2022.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems](https://mlsanity.com/paper/1907.10456/) (2019)
- [Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors](https://mlsanity.com/paper/2006.06356/) (2020)
- [Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control](https://mlsanity.com/paper/1511.03791/) (2015)
- [Towards Adversarially Robust Deep Image Denoising](https://mlsanity.com/paper/2201.04397/) (2022)
- [Subset Scanning Over Neural Network Activations](https://mlsanity.com/paper/1810.08676/) (2018)

## Abstract (arXiv)

We propose using a two-layered deployment of machine learning models to prevent adversarial attacks. The first layer determines whether the data was tampered, while the second layer solves a domain-specific problem. We explore three sets of features and three dataset variations to train machine learning models. Our results show clustering algorithms achieved promising results. In particular, we consider the best results were obtained by applying the DBSCAN algorithm to the structured structural similarity index measure computed between the images and a white reference image.