Improving Network Robustness against Adversarial Attacks with Compact Convolution
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A Rapid Test for Accuracy and Bias of Face Recognition Technology
Sample Correlation for Fingerprinting Deep Face Recognition
Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification
DAAL: Density-Aware Adaptive Line Margin Loss for Multi-Modal Deep Metric Learning
Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priors
LenslessFace: An End-to-End Optimized Lensless System for Privacy-Preserving Face Verification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.