paper-with-me

Papers

Adversarial Attack Driven Data Augmentation for Accurate And Robust Medical Image Segmentation

2021-05-25 · Mst. Tasnim Pervin, Linmi Tao, Aminul Huq, Zuoxiang He, Li Huo

Segmentation is considered to be a very crucial task in medical image analysis. This task has been easier since deep learning models have taken over with its high performing behavior. However, deep learning models dependency on large data proves it to be an obstacle in medical image analysis because of insufficient data samples. Several data augmentation techniques have been used to mitigate this problem. We propose a new augmentation method by introducing adversarial learning attack techniques, specifically Fast Gradient Sign Method (FGSM). Furthermore, We have also introduced the concept of Inverse FGSM (InvFGSM), which works in the opposite manner of FGSM for the data augmentation. This two approaches worked together to improve the segmentation accuracy, as well as helped the model to gain robustness against adversarial attacks. The overall analysis of experiments indicates a novel use of adversarial machine learning along with robustness enhancement.

📄 PDF Abstract BibTeX arXiv:2105.12106

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackData AugmentationDeep LearningImage SegmentationMedical Image AnalysisMedical Image SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

2020-04-29 · EMNLP 2020 11 · John X. Morris, Eli Lifland, Jin Yong Yoo, Jake Grigsby 외

While there has been substantial research using adversarial attacks to analyze NLP models, each attack is implemented in its own code repository. It remains challenging to develop NLP attacks and utilize them to improve …

Adversarial AttackAdversarial TextData AugmentationLexical Entailment+2

Random Transformation of Image Brightness for Adversarial Attack

2021-01-12 · Bo Yang, Kaiyong Xu, Hengjun Wang, Hengwei Zhang

Deep neural networks are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptible perturbations to the original images, but make the model output inaccurate predictions. Before deep neur…

Adversarial AttackData AugmentationImage Augmentation

Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning

2020-12-31 · Chenglei Si, Zhengyan Zhang, Fanchao Qi, Zhiyuan Liu 외

Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to cover more search space of adversarial att…

Adversarial RobustnessData AugmentationText Augmentationtext-classification+1

Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks

2023-03-27 · Tianrui Qin, Xitong Gao, Juanjuan Zhao, Kejiang Ye 외

Unlearnable example attacks are data poisoning techniques that can be used to safeguard public data against unauthorized use for training deep learning models. These methods add stealthy perturbations to the original ima…

Data AugmentationData Poisoning

Achieving Model Robustness through Discrete Adversarial Training

2021-04-11 · EMNLP 2021 11 · Maor Ivgi, Jonathan Berant

Discrete adversarial attacks are symbolic perturbations to a language input that preserve the output label but lead to a prediction error. While such attacks have been extensively explored for the purpose of evaluating m…

model