Are Accuracy and Robustness Correlated?

Abstract

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.

arXiv commentAccepted for publication at ICMLA 2016

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Foveation-based Mechanisms Alleviate Adversarial Examples

Cited by in corpus (18)

• Adversarial Frontier Stitching for Remote Neural Network Watermarking
• Adversarial Examples: Opportunities and Challenges
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• Towards Demystifying Membership Inference Attacks
• Adversarial Examples - A Complete Characterisation of the Phenomenon
• High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
• Adversarial Meta-Learning
• Como funciona o Deep Learning
• Adversarial Examples on Object Recognition: A Comprehensive Survey
• Detection based Defense against Adversarial Examples from the Steganalysis Point of View
• Robustness and Transferability of Universal Attacks on Compressed Models
• On the Effect of Low-Rank Weights on Adversarial Robustness of Neural Networks
• Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks
• Data Quality Matters For Adversarial Training: An Empirical Study
• Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability
• Adversarial Risk Bounds for Neural Networks through Sparsity based Compression
• Robustified Domain Adaptation
• Analyzing Adversarial Robustness of Deep Neural Networks in Pixel Space: a Semantic Perspective