Context-Aware Transfer Attacks for Object Detection

• Main Authors: Cai, Zikui, Xie, Xinxin, Li, Shasha, Yin, Mingjun, Song, Chengyu, Krishnamurthy, Srikanth V., Roy-Chowdhury, Amit K., Asif, M. Salman
• Format: Conference Proceeding
• Language: English
• ISSN: 2159-5399; 2374-3468
• DOI: 10.1609/aaai.v36i1.19889

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 20 percentage points improvement in performance compared to the other state-of-the-art methods.