Are Accuracy and Robustness Correlated?
원문 초록
Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. In this paper, we perform experiments on various adversarial example generation approaches with multiple deep convolutional neural networks including Residual Networks, the best performing models on ImageNet Large-Scale Visual Recognition Challenge 2015. We compare the adversarial example generation techniques with respect to the quality of the produced images, and measure the robustness of the tested machine learning models to adversarial examples. Finally, we conduct large-scale experiments on cross-model adversarial portability. We find that adversarial examples are mostly transferable across similar network topologies, and we demonstrate that better machine learning models are less vulnerable to adversarial examples.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Performing Image Classification for 10 Different Monkey Species using CNN
Statistical characterization and classification of colon microarray gene expression data using multiple machine learning paradigms
Enhanced network anomaly detection based on deep neural networks
ExploreKit: Automatic Feature Generation and Selection
Thumbs up? Sentiment Classification using Machine Learning Techniques
SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
토론
이 논문과 연결된 포럼 글이 아직 없습니다.