Adversarial Defense Through Network Profiling Based Path Extraction
Yuxian Qiu, Jingwen Leng, Cong Guo et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2019
Recently, researchers have started decomposing deep neural network models according to their semantics or functions. Recent work has shown the effectiveness of decomposed functional blocks for defending adversarial attacks, which add small input perturbation to the input image to fool the DNN models. This work proposes a profiling-based method to decompose the DNN models to different functional blocks, which lead to the effective path as a new approach to exploring DNNs' internal organization. Specifically, the per-image effective path can be aggregated to the class-level effective path, through which we observe that adversarial images activate effective path different from normal images. We propose an effective path similarity-based method to detect adversarial images with an interpretable model, which achieve better accuracy and broader applicability than the state-of-the-art technique.
Cited by 42 works. doi:10.1109/cvpr.2019.00491 Open-access PDF
Authors
References
- Deep Residual Learning for Image Recognition
- ImageNet classification with deep convolutional neural networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Backpropagation Applied to Handwritten Zip Code Recognition
- Sequence to Sequence Learning with Neural Networks
- Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
- Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
- Explaining and Harnessing Adversarial Examples
- Towards Evaluating the Robustness of Neural Networks
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images