paper-with-me

홈 › Papers

Adversarially Robust Medical Classification via Attentive Convolutional Neural Networks

2022-10-26 · Isaac Wasserman

Convolutional neural network-based medical image classifiers have been shown to be especially susceptible to adversarial examples. Such instabilities are likely to be unacceptable in the future of automated diagnoses. Though statistical adversarial example detection methods have proven to be effective defense mechanisms, additional research is necessary that investigates the fundamental vulnerabilities of deep-learning-based systems and how best to build models that jointly maximize traditional and robust accuracy. This paper presents the inclusion of attention mechanisms in CNN-based medical image classifiers as a reliable and effective strategy for increasing robust accuracy without sacrifice. This method is able to increase robust accuracy by up to 16% in typical adversarial scenarios and up to 2700% in extreme cases.

📄 PDF Abstract BibTeX arXiv:2210.14405

Code (0)

등록된 구현이 없습니다.

Tasks

Classification

Similar Papers 제목 키워드 기반

Verifiable and Energy Efficient Medical Image Analysis with Quantised Self-attentive Deep Neural Networks

2022-09-30 · Rakshith Sathish, Swanand Khare, Debdoot Sheet

Convolutional Neural Networks have played a significant role in various medical imaging tasks like classification and segmentation. They provide state-of-the-art performance compared to classical image processing algorit…

ClassificationMedical Image AnalysisSegmentationSemantic Segmentation

Understanding Anatomy Classification Through Attentive Response Maps

2016-11-19 · Devinder Kumar, Vlado Menkovski, Graham W. Taylor, Alexander Wong

One of the main challenges for broad adoption of deep learning based models such as convolutional neural networks (CNN), is the lack of understanding of their decisions. In many applications, a simpler, less capable mode…

AnatomyClassificationGeneral Classification

Sparta: Spatially Attentive and Adversarially Robust Activation

2021-05-18 · Qing Guo, Felix Juefei-Xu, Changqing Zhou, Wei Feng 외

Adversarial training (AT) is one of the most effective ways for improving the robustness of deep convolution neural networks (CNNs). Just like common network training, the effectiveness of AT relies on the design of basi…

Learning Interpretable Features via Adversarially Robust Optimization

2019-05-09 · Ashkan Khakzar, Shadi Albarqouni, Nassir Navab

Neural networks are proven to be remarkably successful for classification and diagnosis in medical applications. However, the ambiguity in the decision-making process and the interpretability of the learned features is a…

Decision Making

Sparta: Spatially Attentive and Adversarially Robust Activations

2021-01-01 · Qing Guo, Felix Juefei-Xu, Changqing Zhou, Lei Ma 외

Adversarial training has been demonstrated to be useful for improving the robustness of deep neural networks (DNNs). However, the impacts of basic network components (e.g., ReLU, the widely used activation function for D…

Denoising