Compression-Resistant Backdoor Attack against Deep Neural Networks. (arXiv:2201.00672v1 [cs.CV])

In recent years, many backdoor attacks based on training data poisoning have
been proposed. However, in practice, those backdoor attacks are vulnerable to
image compressions. When backdoor instances are compressed, the feature of
specific backdoor trigger will be destroyed, which could result in the backdoor
attack performance deteriorating. In this paper, we propose a
compression-resistant backdoor attack based on feature consistency training. To
the best of our knowledge, this is the first backdoor attack that is robust to
image compressions. …

arxiv compression cv networks neural networks