Model X-ray:Detect Backdoored Models via Decision Boundary

arXiv:2402.17465v1 Announce Type: cross
Abstract: Deep neural networks (DNNs) have revolutionized various industries, leading to the rise of Machine Learning as a Service (MLaaS). In this paradigm, well-trained models are typically deployed through APIs. However, DNNs are susceptible to backdoor attacks, which pose significant risks to their applications. This vulnerability necessitates a method for users to ascertain whether an API is compromised before usage. Although many backdoor detection methods have been developed, they often operate under the assumption that the …

abstract apis applications arxiv attacks backdoor cs.cr cs.cv decision industries machine machine learning networks neural networks paradigm ray risks service through type via vulnerability x-ray