# Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Models

arXiv: https://arxiv.org/abs/2409.06420 · HTML: https://mlsanity.com/paper/2409.06420/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 55 references that are in the map.
- First posted on arXiv 10 Sep 2024.

## Builds on (most cited first, 26 of 26)

- [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)
- [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)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression](https://mlsanity.com/paper/1705.02900/) (2017)
- [Image Super-Resolution as a Defense Against Adversarial Attacks](https://mlsanity.com/paper/1901.01677/) (2019)
- [When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture](https://mlsanity.com/paper/2210.07540/) (2022)
- [CFA: Class-wise Calibrated Fair Adversarial Training](https://mlsanity.com/paper/2303.14460/) (2023)
- [Mind the box: l1-APGD for sparse adversarial attacks on image classifiers](https://mlsanity.com/paper/2103.01208/) (2021)
- [PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators](https://mlsanity.com/paper/2306.08918/) (2023)
- [Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond](https://mlsanity.com/paper/2203.16931/) (2022)
- [AdvHaze: Adversarial Haze Attack](https://mlsanity.com/paper/2104.13673/) (2021)
- [Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration](https://mlsanity.com/paper/2106.07910/) (2021)
- [Underwater Image Enhancement based on Deep Learning and Image Formation Model](https://mlsanity.com/paper/2101.00991/) (2021)
- [Underwater Image Enhancement via Learning Water Type Desensitized Representations](https://mlsanity.com/paper/2102.00676/) (2021)
- [Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement](https://mlsanity.com/paper/2211.10608/) (2022)
- [WaterFlow: Heuristic Normalizing Flow for Underwater Image Enhancement and Beyond](https://mlsanity.com/paper/2308.00931/) (2023)
- [Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss](https://mlsanity.com/paper/1908.00274/) (2019)

## Abstract (arXiv)

Learning-based methods for underwater image enhancement (UWIE) have undergone extensive exploration. However, learning-based models are usually vulnerable to adversarial examples so as the UWIE models. To the best of our knowledge, there is no comprehensive study on the adversarial robustness of UWIE models, which indicates that UWIE models are potentially under the threat of adversarial attacks. In this paper, we propose a general adversarial attack protocol. We make a first attempt to conduct adversarial attacks on five well-designed UWIE models on three common underwater image benchmark datasets. Considering the scattering and absorption of light in the underwater environment, there exists a strong correlation between color correction and underwater image enhancement. On the basis of that, we also design two effective UWIE-oriented adversarial attack methods Pixel Attack and Color Shift Attack targeting different color spaces. The results show that five models exhibit varying degrees of vulnerability to adversarial attacks and well-designed small perturbations on degraded images are capable of preventing UWIE models from generating enhanced results. Further, we conduct adversarial training on these models and successfully mitigated the effectiveness of adversarial attacks. In summary, we reveal the adversarial vulnerability of UWIE models and propose a new evaluation dimension of UWIE models.