Improving Resistance to Adversarial Deformations by Regularizing Gradients
Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. However, most defense methods are designed to defend against intensity perturbations and ignore location perturbations, which should be equally important for deep model security. In this paper, we focus on adversarial deformations, a typical class of location perturbations, and propose a flow gradient regularization to improve the resistance of models. Theoretically, we prove that, compared with input gradient regularization, regularizing flow gradients is able to get a tighter bound. Over multiple datasets, architectures, and adversarial deformations, our empirical results indicate that models trained with flow gradients can acquire a better resistance than trained with input gradients with a large margin, and also better than adversarial training. Moreover, compared with directly training with adversarial deformations, our method can achieve better results in unseen attacks, and combining these two methods can improve the resistance further.
Code (1)
Similar Papers 제목 키워드 기반
Improving Back-Propagation by Adding an Adversarial Gradient
The back-propagation algorithm is widely used for learning in artificial neural networks. A challenge in machine learning is to create models that generalize to new data samples not seen in the training data. Recently, a…
BIG-bench Machine LearningGeneral ClassificationCharacterizing Model Robustness via Natural Input Gradients
Adversarially robust models are locally smooth around each data sample so that small perturbations cannot drastically change model outputs. In modern systems, such smoothness is usually obtained via Adversarial Training,…
modelImproving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the…
Adversarial RobustnessTowards Robust Training of Neural Networks by Regularizing Adversarial Gradients
In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating pos…
Neural Networks with Structural Resistance to Adversarial Attacks
In adversarial attacks to machine-learning classifiers, small perturbations are added to input that is correctly classified. The perturbations yield adversarial examples, which are virtually indistinguishable from the un…