On the Effect of Pruning on Adversarial Robustness
Pruning is a well-known mechanism for reducing the computational cost of deep convolutional networks. However, studies have shown the potential of pruning as a form of regularization, which reduces overfitting and improves generalization. We demonstrate that this family of strategies provides additional benefits beyond computational performance and generalization. Our analyses reveal that pruning structures (filters and/or layers) from convolutional networks increase not only generalization but also robustness to adversarial images (natural images with content modified). Such achievements are possible since pruning reduces network capacity and provides regularization, which have been proven effective tools against adversarial images. In contrast to promising defense mechanisms that require training with adversarial images and careful regularization, we show that pruning obtains competitive results considering only natural images (e.g., the standard and low-cost training). We confirm these findings on several adversarial attacks and architectures; thus suggesting the potential of pruning as a novel defense mechanism against adversarial images.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks
Neural network pruning has shown to be an effective technique for reducing the network size, trading desirable properties like generalization and robustness to adversarial attacks for higher sparsity. Recent work has cla…
Network PruningS2AP: Score-space Sharpness Minimization for Adversarial Pruning
Adversarial pruning methods have emerged as a powerful tool for compressing neural networks while preserving robustness against adversarial attacks. These methods typically follow a three-step pipeline: (i) pretrain a ro…
Blind Adversarial Pruning: Balance Accuracy, Efficiency and Robustness
With the growth of interest in the attack and defense of deep neural networks, researchers are focusing more on the robustness of applying them to devices with limited memory. Thus, unlike adversarial training, which onl…
Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning
The prevalence and success of Deep Neural Network (DNN) applications in recent years have motivated research on DNN compression, such as pruning and quantization. These techniques accelerate model inference, reduce power…
Adversarial RobustnessQuantizationPruning Adversarially Robust Neural Networks without Adversarial Examples
Adversarial pruning compresses models while preserving robustness. Current methods require access to adversarial examples during pruning. This significantly hampers training efficiency. Moreover, as new adversarial attac…
Adversarial Robustness