# DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation

arXiv: https://arxiv.org/abs/1908.05195 · HTML: https://mlsanity.com/paper/1908.05195/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2019.

## Built on by (most cited first, 14 of 14)

- [Dataset Distillation: A Comprehensive Review](https://mlsanity.com/paper/2301.07014/) (2023)
- [SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness](https://mlsanity.com/paper/2207.12391/) (2022)
- [Backdoor Attacks Against Dataset Distillation](https://mlsanity.com/paper/2301.01197/) (2023)
- [Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models](https://mlsanity.com/paper/2306.12941/) (2023)
- [Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation](https://mlsanity.com/paper/2310.17436/) (2023)
- [Towards Adversarial Purification using Denoising AutoEncoders](https://mlsanity.com/paper/2208.13838/) (2022)
- [Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentation](https://mlsanity.com/paper/2305.12825/) (2023)
- [Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training](https://mlsanity.com/paper/2402.12187/) (2024)
- [Transferable Attack for Semantic Segmentation](https://mlsanity.com/paper/2307.16572/) (2023)
- [Prompt Backdoors in Visual Prompt Learning](https://mlsanity.com/paper/2310.07632/) (2023)
- [A deep learning model for burn depth classification using ultrasound imaging](https://mlsanity.com/paper/2203.15879/) (2022)
- [Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis](https://mlsanity.com/paper/2408.10021/) (2024)
- [On-Manifold Projected Gradient Descent](https://mlsanity.com/paper/2308.12279/) (2023)
- [BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning](https://mlsanity.com/paper/2605.31246/) (2026)

## Abstract (arXiv)

Nowadays, Deep learning techniques show dramatic performance on computer vision area, and they even outperform human. But it is also vulnerable to some small perturbation called an adversarial attack. This is a problem combined with the safety of artificial intelligence, which has recently been studied a lot. These attacks have shown that they can fool models of image classification, semantic segmentation, and object detection. We point out this attack can be protected by denoise autoencoder, which is used for denoising the perturbation and restoring the original images. We experiment with various noise distributions and verify the effect of denoise autoencoder against adversarial attack in semantic segmentation.