Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification
Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the AT. In this paper, in order to reserve high generalization while improving robustness, we proposed a dynamic perturbation-adaptive adversarial training (DPAAT) method, which placed AT in a dynamic learning environment to generate adaptive data-level perturbations and provided a dynamically updated criterion by loss information collections to handle the disadvantage of fixed perturbation sizes in conventional AT methods and the dependence on external transference. Comprehensive testing on dermatology HAM10000 dataset showed that the DPAAT not only achieved better robustness improvement and generalization preservation but also significantly enhanced mean average precision and interpretability on various CNNs, indicating its great potential as a generic adversarial training method on the MIC.
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationMedical Image ClassificationSimilar Papers 제목 키워드 기반
Dynamic Epsilon Scheduling: A Multi-Factor Adaptive Perturbation Budget for Adversarial Training
Adversarial training is among the most effective strategies for defending deep neural networks against adversarial examples. A key limitation of existing adversarial training approaches lies in their reliance on a fixed …
Adversarial RobustnessSchedulingRobust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the …
Deep Reinforcement LearningMuJoCoIncreasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural Networks
Deep neural networks (DNNs) are vulnerable to adversarial noises. By adding adversarial noises to training samples, adversarial training can improve the model's robustness against adversarial noises. However, adversarial…
Adversarial RobustnessGeneral ClassificationImage ClassificationImage Segmentation+3Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking
We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite. The introduced environments allow auto-differentiat…
BenchmarkingOpenAI GymAdaptive Epsilon Adversarial Training for Robust Gravitational Wave Parameter Estimation Using Normalizing Flows
Adversarial training with Normalizing Flow (NF) models is an emerging research area aimed at improving model robustness through adversarial samples. In this study, we focus on applying adversarial training to NF models f…
parameter estimation