Flutterby™! : Backdoors in machine learning models

IEEE Xplore: Planting Undetectable Backdoors in Machine Learning Models.

Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. Delegation of learning has clear benefits, and at the same time raises serious concerns of trust. This work studies possible abuses of power by untrusted learners. We show how a malicious learner can plant an undetectable backdoor into a classifier.