Improving Network Robustness against Adversarial Attacks with Compact Convolution
arXiv:1712.00699
Abstract
Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by adversarial attacks. These attacks add a small perturbation to the input image that causes the network to misclassify the sample. In this paper, we focus on neutralizing adversarial attacks by compact feature learning. In particular, we show that learning features in a closed and bounded space improves the robustness of the network. We explore the effect of L2-Softmax Loss, that enforces compactness in the learned features, thus resulting in enhanced robustness to adversarial perturbations. Additionally, we propose compact convolution, a novel method of convolution that when incorporated in conventional CNNs improves their robustness. Compact convolution ensures feature compactness at every layer such that they are bounded and close to each other. Extensive experiments show that Compact Convolutional Networks (CCNs) neutralize multiple types of attacks, and perform better than existing methods in defending adversarial attacks, without incurring any additional training overhead compared to CNNs.
References in corpus (12)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Ensemble Adversarial Training: Attacks and Defenses
- Towards Deep Neural Network Architectures Robust to Adversarial Examples
- Countering Adversarial Images using Input Transformations
- Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization
- Detecting Adversarial Samples from Artifacts
- On the (Statistical) Detection of Adversarial Examples
- A study of the effect of JPG compression on adversarial images
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
- Parseval Networks: Improving Robustness to Adversarial Examples
- Universal adversarial perturbations
- SafetyNet: Detecting and Rejecting Adversarial Examples Robustly
Cited by in corpus (5)
- Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective
- Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression
- Generating 3D Adversarial Point Clouds
- ShapeAdv: Generating Shape-Aware Adversarial 3D Point Clouds
- Defense-guided Transferable Adversarial Attacks