PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks

Abstract

Deep learning systems have become ubiquitous in many aspects of our lives. Unfortunately, it has been shown that such systems are vulnerable to adversarial attacks, making them prone to potential unlawful uses. Designing deep neural networks that are robust to adversarial attacks is a fundamental step in making such systems safer and deployable in a broader variety of applications (e.g. autonomous driving), but more importantly is a necessary step to design novel and more advanced architectures built on new computational paradigms rather than marginally building on the existing ones. In this paper we introduce PeerNets, a novel family of convolutional networks alternating classical Euclidean convolutions with graph convolutions to harness information from a graph of peer samples. This results in a form of non-local forward propagation in the model, where latent features are conditioned on the global structure induced by the graph, that is up to 3 times more robust to a variety of white- and black-box adversarial attacks compared to conventional architectures with almost no drop in accuracy.

References in corpus (20)

• Semi-Supervised Classification with Graph Convolutional Networks
• Intriguing properties of neural networks
• Deep Residual Learning for Image Recognition
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Spectral Networks and Locally Connected Networks on Graphs
• Ensemble Adversarial Training: Attacks and Defenses
• Deep Convolutional Networks on Graph-Structured Data
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Few-Shot Learning with Graph Neural Networks
• SfM-Net: Learning of Structure and Motion from Video
• Dynamic Graph CNN for Learning on Point Clouds
• Non-local Neural Networks
• DeepFool: a simple and accurate method to fool deep neural networks
• Universal adversarial perturbations
• On the Effectiveness of Defensive Distillation
• Video Frame Interpolation via Adaptive Convolution
• Temporal Dynamic Graph LSTM for Action-driven Video Object Detection
• LDMNet: Low Dimensional Manifold Regularized Neural Networks

Cited by in corpus (4)

• Learning to Detect Objects with a 1 Megapixel Event Camera
• Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking
• Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustness
• Are You Tampering With My Data?