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 20 percentage points improvement in performance compared to the other state-of-the-art methods. |
Year | Venue | Keywords |
---|---|---|
2022 | AAAI Conference on Artificial Intelligence | Computer Vision (CV),Machine Learning (ML) |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zikui Cai | 1 | 0 | 1.35 |
Xinxin Xie | 2 | 0 | 0.34 |
Shasha Li | 3 | 8 | 2.18 |
Mingjun Yin | 4 | 0 | 0.68 |
Chengyu Song | 5 | 412 | 30.15 |
Srikanth V. Krishnamurthy | 6 | 645 | 61.55 |
Amit K. Roy Chowdhury | 7 | 1153 | 73.96 |
M. Salman Asif | 8 | 14 | 5.59 |