Backdoor Attacks for Remote Sensing Data with Wavelet Transform. (arXiv:2211.08044v1 [cs.CV])

Recent years have witnessed the great success of deep learning algorithms in
the geoscience and remote sensing realm. Nevertheless, the security and
robustness of deep learning models deserve special attention when addressing
safety-critical remote sensing tasks. In this paper, we provide a systematic
analysis of backdoor attacks for remote sensing data, where both scene
classification and semantic segmentation tasks are considered. While most of
the existing backdoor attack algorithms rely on visible triggers like squared
patches with well-designed patterns, we …

arxiv attacks backdoor data remote sensing wavelet