Adversarial Patch Attacks on Monocular Depth Estimation Networks

Abstract

Thanks to the excellent learning capability of deep convolutional neural networks (CNN), monocular depth estimation using CNNs has achieved great success in recent years. However, depth estimation from a monocular image alone is essentially an ill-posed problem, and thus, it seems that this approach would have inherent vulnerabilities. To reveal this limitation, we propose a method of adversarial patch attack on monocular depth estimation. More specifically, we generate artificial patterns (adversarial patches) that can fool the target methods into estimating an incorrect depth for the regions where the patterns are placed. Our method can be implemented in the real world by physically placing the printed patterns in real scenes. We also analyze the behavior of monocular depth estimation under attacks by visualizing the activation levels of the intermediate layers and the regions potentially affected by the adversarial attack.

arXiv commentPublisher's Open Access PDF with the CC-BY copyright. Associated video, data and programs are available at https://www.fujii.nuee.nagoya-u.ac.jp/Research/MonoDepth/

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Distilling the Knowledge in a Neural Network
• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
• Evasion Attacks against Machine Learning at Test Time
• Synthesizing Robust Adversarial Examples
• DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling
• From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
• AdvHat: Real-world adversarial attack on ArcFace Face ID system
• NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles
• Adversarial Attacks on Monocular Depth Estimation

Cited by in corpus (2)

• On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving
• CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Models