Backdoor Attacks on Vision Transformers. (arXiv:2206.08477v1 [cs.CV])

Web: http://arxiv.org/abs/2206.08477

Vision Transformers (ViT) have recently demonstrated exemplary performance on
a variety of vision tasks and are being used as an alternative to CNNs. Their
design is based on a self-attention mechanism that processes images as a
sequence of patches, which is quite different compared to CNNs. Hence it is
interesting to study if ViTs are vulnerable to backdoor attacks. Backdoor
attacks happen when an attacker poisons a small part of the training data for
malicious purposes. The model performance is …

arxiv attacks cv on transformers vision