Self-supervised Adversarial Training
Recent work has demonstrated that neural networks are vulnerable to adversarial examples. To escape from the predicament, many works try to harden the model in various ways, in which adversarial training is an effective way which learns robust feature representation so as to resist adversarial attacks. Meanwhile, the self-supervised learning aims to learn robust and semantic embedding from data itself. With these views, we introduce self-supervised learning to against adversarial examples in this paper. Specifically, the self-supervised representation coupled with k-Nearest Neighbour is proposed for classification. To further strengthen the defense ability, self-supervised adversarial training is proposed, which maximizes the mutual information between the representations of original examples and the corresponding adversarial examples. Experimental results show that the self-supervised representation outperforms its supervised version in respect of robustness and self-supervised adversarial training can further improve the defense ability efficiently.
Code (1)
Tasks
Self-Supervised LearningSimilar Papers 제목 키워드 기반
Online Adversarial Purification based on Self-supervised Learning
Deep neural networks are known to be vulnerable to adversarial examples, where a perturbation in the input space leads to an amplified shift in the latent network representation. In this paper, we combine canonical super…
Adversarial PurificationRepresentation LearningSelf-Supervised LearningOnline Adversarial Purification based on Self-Supervision
Deep neural networks are known to be vulnerable to adversarial examples, where a perturbation in the input space leads to an amplified shift in the latent network representation. In this paper, we combine canonical super…
Adversarial PurificationRepresentation LearningImproving Adversarial Defense with Self-supervised Test-time Fine-tuning
Although adversarial training and its variants currently constitute the most effective way to achieve robustness against adversarial attacks, their poor generalization limits their performance on the test samples. In thi…
Adversarial DefenseImproving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training
Learning a self-supervised Monocular Depth Estimation (MDE) model with great generalization remains significantly challenging. Despite the success of adversarial augmentation in the supervised learning generalization, na…
Data AugmentationDepth EstimationDomain GeneralizationMonocular Depth EstimationAdversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks
Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks, especially the physical ones, pose a great threat to the…
Adversarial RobustnessAutonomous DrivingContrastive LearningDepth Estimation+1