Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger. (arXiv:2302.14677v1 [cs.CV])

Recent deep-learning-based compression methods have achieved superior
performance compared with traditional approaches. However, deep learning models
have proven to be vulnerable to backdoor attacks, where some specific trigger
patterns added to the input can lead to malicious behavior of the models. In
this paper, we present a novel backdoor attack with multiple triggers against
learned image compression models. Motivated by the widely used discrete cosine
transform (DCT) in existing compression systems and standards, we propose a
frequency-based trigger injection model …

attack attacks backdoor backdoor attacks compression deep learning input malicious malicious behavior novel patterns performance trigger vulnerable