ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms. (arXiv:2302.11408v1 [cs.LG])

Backdoor data detection is traditionally studied in an end-to-end supervised
learning (SL) setting. However, recent years have seen the proliferating
adoption of self-supervised learning (SSL) and transfer learning (TL), due to
their lesser need for labeled data. Successful backdoor attacks have also been
demonstrated in these new settings. However, we lack a thorough understanding
of the applicability of existing detection methods across a variety of learning
settings. By evaluating 56 attack settings, we show that the performance of
most existing …

adoption asset attacks backdoor backdoor attacks data data detection deep learning detection end end-to-end settings ssl understanding