# Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning

arXiv: https://arxiv.org/abs/2305.11347 · HTML: https://mlsanity.com/paper/2305.11347/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 33 of its 46 references that are in the map.
- First posted on arXiv 18 May 2023.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 30 of 33)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [Adversarial Examples for Semantic Segmentation and Object Detection](https://mlsanity.com/paper/1703.08603/) (2017)
- [SpaceNet: A Remote Sensing Dataset and Challenge Series](https://mlsanity.com/paper/1807.01232/) (2018)
- [On the Robustness of Semantic Segmentation Models to Adversarial Attacks](https://mlsanity.com/paper/1711.09856/) (2017)
- [Benchmarking the Robustness of Semantic Segmentation Models](https://mlsanity.com/paper/1908.05005/) (2019)
- [Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning](https://mlsanity.com/paper/2205.01992/) (2022)
- [A review: Deep learning for medical image segmentation using multi-modality fusion](https://mlsanity.com/paper/2004.10664/) (2020)
- [SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness](https://mlsanity.com/paper/2207.12391/) (2022)
- [Multimodal Deep Learning for Robust RGB-D Object Recognition](https://mlsanity.com/paper/1507.06821/) (2015)
- [Motivating the Rules of the Game for Adversarial Example Research](https://mlsanity.com/paper/1807.06732/) (2018)
- [Hidden Backdoor Attack against Semantic Segmentation Models](https://mlsanity.com/paper/2103.04038/) (2021)
- [Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers](https://mlsanity.com/paper/2010.05495/) (2020)
- [Reliability in Semantic Segmentation: Are We on the Right Track?](https://mlsanity.com/paper/2303.11298/) (2023)
- [On Single Source Robustness in Deep Fusion Models](https://mlsanity.com/paper/1906.04691/) (2019)
- [Investigating Vulnerability to Adversarial Examples on Multimodal Data Fusion in Deep Learning](https://mlsanity.com/paper/2005.10987/) (2020)
- [Adversarial Attacks against a Satellite-borne Multispectral Cloud Detector](https://mlsanity.com/paper/2112.01723/) (2021)

## Built on by (most cited first, 1 of 1)

- [Impact of architecture on robustness and interpretability of multispectral deep neural networks](https://mlsanity.com/paper/2309.12463/) (2023)

## Abstract (arXiv)

In overhead image segmentation tasks, including additional spectral bands beyond the traditional RGB channels can improve model performance. However, it is still unclear how incorporating this additional data impacts model robustness to adversarial attacks and natural perturbations. For adversarial robustness, the additional information could improve the model's ability to distinguish malicious inputs, or simply provide new attack avenues and vulnerabilities. For natural perturbations, the additional information could better inform model decisions and weaken perturbation effects or have no significant influence at all. In this work, we seek to characterize the performance and robustness of a multispectral (RGB and near infrared) image segmentation model subjected to adversarial attacks and natural perturbations. While existing adversarial and natural robustness research has focused primarily on digital perturbations, we prioritize on creating realistic perturbations designed with physical world conditions in mind. For adversarial robustness, we focus on data poisoning attacks whereas for natural robustness, we focus on extending ImageNet-C common corruptions for fog and snow that coherently and self-consistently perturbs the input data. Overall, we find both RGB and multispectral models are vulnerable to data poisoning attacks regardless of input or fusion architectures and that while physically realizable natural perturbations still degrade model performance, the impact differs based on fusion architecture and input data.