Fast Local Attack: Generating Local Adversarial Examples for Object Detectors

Abstract

The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object detectors, but they generate globally perturbation on the whole image, which is unnecessary. In our work, we leverage higher-level semantic information to generate high aggressive local perturbations for anchor-free object detectors. As a result, it is less computationally intensive and achieves a higher black-box attack as well as transferring attack performance. The adversarial examples generated by our method are not only capable of attacking anchor-free object detectors, but also able to be transferred to attack anchor-based object detector.

arXiv commentPublished in: 2020 International Joint Conference on Neural Networks (IJCNN)

References in corpus (11)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Robust Physical-World Attacks on Deep Learning Models
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• A study of the effect of JPG compression on adversarial images
• Generating Adversarial Examples with Adversarial Networks
• Adversarial Transformation Networks: Learning to Generate Adversarial Examples
• Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack
• Adversarial Images for Variational Autoencoders
• Curls & Whey: Boosting Black-Box Adversarial Attacks
• MeshAdv: Adversarial Meshes for Visual Recognition