Robust Adversarial Perturbation on Deep Proposal-based Models

Abstract

Adversarial noises are useful tools to probe the weakness of deep learning based computer vision algorithms. In this paper, we describe a robust adversarial perturbation (R-AP) method to attack deep proposal-based object detectors and instance segmentation algorithms. Our method focuses on attacking the common component in these algorithms, namely Region Proposal Network (RPN), to universally degrade their performance in a black-box fashion. To do so, we design a loss function that combines a label loss and a novel shape loss, and optimize it with respect to image using a gradient based iterative algorithm. Evaluations are performed on the MS COCO 2014 dataset for the adversarial attacking of 6 state-of-the-art object detectors and 2 instance segmentation algorithms. Experimental results demonstrate the efficacy of the proposed method.

To appear in BMVC 2018

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Intriguing properties of neural networks
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Robust Physical-World Attacks on Deep Learning Models
• An Implementation of Faster RCNN with Study for Region Sampling
• Adversarial Examples that Fool Detectors
• Adversarial Examples for Semantic Segmentation and Object Detection
• Adversarial Attacks Beyond the Image Space

Cited by in corpus (11)

• Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images
• Transferable Adversarial Attacks for Image and Video Object Detection
• Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving
• DPAttack: Diffused Patch Attacks against Universal Object Detection
• Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
• Adversarial Feature Augmentation and Normalization for Visual Recognition
• Category-wise Attack: Transferable Adversarial Examples for Anchor Free Object Detection
• SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking
• Detection as Regression: Certified Object Detection by Median Smoothing
• Understanding Object Detection Through An Adversarial Lens
• Universal Physical Camouflage Attacks on Object Detectors