Image Transformation can make Neural Networks more robust against Adversarial Examples

Abstract

Neural networks are being applied in many tasks related to IoT with encouraging results. For example, neural networks can precisely detect human, objects and animal via surveillance camera for security purpose. However, neural networks have been recently found vulnerable to well-designed input samples that called adversarial examples. Such issue causes neural networks to misclassify adversarial examples that are imperceptible to humans. We found giving a rotation to an adversarial example image can defeat the effect of adversarial examples. Using MNIST number images as the original images, we first generated adversarial examples to neural network recognizer, which was completely fooled by the forged examples. Then we rotated the adversarial image and gave them to the recognizer to find the recognizer to regain the correct recognition. Thus, we empirically confirmed rotation to images can protect pattern recognizer based on neural networks from adversarial example attacks.

References in corpus (9)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Sequence to Sequence Learning with Neural Networks
• WaveNet: A Generative Model for Raw Audio
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Convolutional Neural Networks for Sentence Classification
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Defensive Distillation is Not Robust to Adversarial Examples
• Generating Adversarial Examples with Adversarial Networks
• Biologically inspired protection of deep networks from adversarial attacks

Cited by in corpus (6)

• Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning
• Ptolemy: Architecture Support for Robust Deep Learning
• Robust Invisible Hyperlinks in Physical Photographs Based on 3D Rendering Attacks
• Search Space of Adversarial Perturbations against Image Filters
• Integrating Motion into Vision Models for Better Visual Prediction
• An Efficient Pre-processing Method to Eliminate Adversarial Effects