An Embarrassingly Simple Defense Against Backdoor Attacks On SSL

arXiv:2403.15918v1 Announce Type: new
Abstract: Self Supervised Learning (SSL) has emerged as a powerful paradigm to tackle data landscapes with absence of human supervision. The ability to learn meaningful tasks without the use of labeled data makes SSL a popular method to manage large chunks of data in the absence of labels. However, recent work indicates SSL to be vulnerable to backdoor attacks, wherein models can be controlled, possibly maliciously, to suit an adversary's motives. Li et.al (2022) introduce a …

arxiv attacks backdoor cs.cv defense simple ssl type