Re-thinking model robustness from stability: a new insight to defend adversarial examples
- 14 June 2022
- journal article
- research article
- Published by Springer Nature in Machine Learning
- Vol. 111 (7) , 2489-2513
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (no.61876155and no.61876154)
This publication has 10 references indexed in Scilit:
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Adversarial Examples for Generative Models2018
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks2018
- Mask R-CNN2017
- Analysis of classifiers’ robustness to adversarial perturbationsMachine Learning, 2017
- Densely Connected Convolutional Networks2017
- Wide Residual Networks2016
- A Unified Gradient Regularization Family for Adversarial Examples2015
- Deep learningNature, 2015
- On the limited memory BFGS method for large scale optimizationMathematical Programming, 1989