Robustification of Segmentation Models Against Adversarial Perturbations In Medical Imaging

2020-09-23 · Hanwool Park, Amirhossein Bayat, Mohammad Sabokrou, Jan S. Kirschke, Bjoern H. Menze

This paper presents a novel yet efficient defense framework for segmentation models against adversarial attacks in medical imaging. In contrary to the defense methods against adversarial attacks for classification models which widely are investigated, such defense methods for segmentation models has been less explored. Our proposed method can be used for any deep learning models without revising the target deep learning models, as well as can be independent of adversarial attacks. Our framework consists of a frequency domain converter, a detector, and a reformer. The frequency domain converter helps the detector detects adversarial examples by using a frame domain of an image. The reformer helps target models to predict more precisely. We have experiments to empirically show that our proposed method has a better performance compared to the existing defense method.

📄 PDF Abstract BibTeX arXiv:2009.11090

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningSegmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

LSH Attention 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Adversarial and Natural Perturbations for General Robustness

2020-10-03 · Sadaf Gulshad, Jan Hendrik Metzen, Arnold Smeulders

In this paper we aim to explore the general robustness of neural network classifiers by utilizing adversarial as well as natural perturbations. Different from previous works which mainly focus on studying the robustness …

Characterization of the equivalence of robustification and regularization in linear and matrix regression

2014-11-22 · Dimitris Bertsimas, Martin S. Copenhaver

The notion of developing statistical methods in machine learning which are robust to adversarial perturbations in the underlying data has been the subject of increasing interest in recent years. A common feature of this …

Matrix Completion regression

Efficient Preemptive Robustification with Image Sharpening

2026-03-26 · Jiaming Liang, Chi-Man Pun arxiv

Despite their great success, deep neural networks rely on high-dimensional, non-robust representations, making them vulnerable to imperceptible perturbations, even in transfer scenarios. To address this, both training-ti…

Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks

2019-04-27 · Xiang He, Sibei Yang, Guanbin Li?, Haofeng Li 외

Recent progress in biomedical image segmentation based on deep convolutional neural networks (CNNs) has drawn much attention. However, its vulnerability towards adversarial samples cannot be overlooked. This paper is the…

Image Segmentation Lesion Segmentation Segmentation Semantic Segmentation+1

Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks

2021-12-10 · Seungyong Moon, Gaon An, Hyun Oh Song

Deep neural networks have become the driving force of modern image recognition systems. However, the vulnerability of neural networks against adversarial attacks poses a serious threat to the people affected by these sys…