English

Context-Aware Transfer Attacks for Object Detection

Computer Vision and Pattern Recognition 2021-12-07 v1 Artificial Intelligence Machine Learning

Abstract

Blackbox transfer attacks for image classifiers have been extensively studied in recent years. In contrast, little progress has been made on transfer attacks for object detectors. Object detectors take a holistic view of the image and the detection of one object (or lack thereof) often depends on other objects in the scene. This makes such detectors inherently context-aware and adversarial attacks in this space are more challenging than those targeting image classifiers. In this paper, we present a new approach to generate context-aware attacks for object detectors. We show that by using co-occurrence of objects and their relative locations and sizes as context information, we can successfully generate targeted mis-categorization attacks that achieve higher transfer success rates on blackbox object detectors than the state-of-the-art. We test our approach on a variety of object detectors with images from PASCAL VOC and MS COCO datasets and demonstrate up to 2020 percentage points improvement in performance compared to the other state-of-the-art methods.

Keywords

Cite

@article{arxiv.2112.03223,
  title  = {Context-Aware Transfer Attacks for Object Detection},
  author = {Zikui Cai and Xinxin Xie and Shasha Li and Mingjun Yin and Chengyu Song and Srikanth V. Krishnamurthy and Amit K. Roy-Chowdhury and M. Salman Asif},
  journal= {arXiv preprint arXiv:2112.03223},
  year   = {2021}
}

Comments

accepted to AAAI 2022

R2 v1 2026-06-24T08:06:24.182Z