Improving Adversarial Robustness by Encouraging Discriminative Features
Deep neural networks (DNNs) have achieved state-of-the-art results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.e. inputs that are specifically crafted by an adversary to cause DNNs to misbehave, questioning the security and reliability of applications. In this paper, we encourage DNN classifiers to learn more discriminative features by imposing a center loss in addition to the regular softmax cross-entropy loss. Intuitively, the center loss encourages DNNs to simultaneously learns a center for the deep features of each class, and minimize the distances between the intra-class deep features and their corresponding class centers. We hypothesize that minimizing distances between intra-class features and maximizing the distances between inter-class features at the same time would improve a classifier's robustness to adversarial examples. Our results on state-of-the-art architectures on MNIST, CIFAR-10, and CIFAR-100 confirmed that intuition and highlight the importance of discriminative features.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Discriminative Robust Transformation Learning
This paper proposes a framework for learning features that are robust to data variation, which is particularly important when only a limited number of trainingsamples are available. The framework makes it possible to tra…
Push Stricter to Decide Better: A Class-Conditional Feature Adaptive Framework for Improving Adversarial Robustness
In response to the threat of adversarial examples, adversarial training provides an attractive option for enhancing the model robustness by training models on online-augmented adversarial examples. However, most of the e…
Adversarial RobustnessRethinking Clustering for Robustness
This paper studies how encouraging semantically-aligned features during deep neural network training can increase network robustness. Recent works observed that Adversarial Training leads to robust models, whose learnt f…
ClusteringA Robust Adversarial Ensemble with Causal (Feature Interaction) Interpretations for Image Classification
Deep learning-based discriminative classifiers, despite their remarkable success, remain vulnerable to adversarial examples that can mislead model predictions. While adversarial training can enhance robustness, it fails …
Adversarial Robustnesscounterfactualimage-classificationImage ClassificationTowards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features
Adversarial attacks have been widely studied for general classification tasks, but remain unexplored in the context of fine-grained recognition, where the inter-class similarities facilitate the attacker's task. In this …
General Classification