Undetectable Backdoors in Machine-Learning Models

Minimalist · Apr 19, 2022

Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. We show how a malicious learner can plant an undetectable backdoor into a classifier. On the surface, such a backdoored classifier behaves normally, but in reality, the learner maintains a mechanism for changing the classification of any input, with only a slight perturbation. Importantly, without the appropriate “backdoor key”, the mechanism is hidden and cannot be detected by any computationally-bounded observer. We demonstrate two frameworks for planting undetectable backdoors, with incomparable guarantees.
Click to expand...

https://www.schneier.com/blog/archi...ble-backdoors-in-machine-learning-models.html

Log in or Sign up

Undetectable Backdoors in Machine-Learning Models

Minimalist Registered Member

Log in or Sign up

Undetectable Backdoors in Machine-Learning Models

Minimalist Registered Member

Useful Searches