Reliable Learning for Test-time Attacks and Distribution Shift. (arXiv:2304.03370v1 [cs.LG])

Machine learning algorithms are often used in environments which are not
captured accurately even by the most carefully obtained training data, either
due to the possibility of `adversarial' test-time attacks, or on account of
`natural' distribution shift. For test-time attacks, we introduce and analyze a
novel robust reliability guarantee, which requires a learner to output
predictions along with a reliability radius $\eta$, with the meaning that its
prediction is guaranteed to be correct as long as the adversary has not …

account adversarial adversary algorithms attacks data distribution environments guarantee machine machine learning machine learning algorithms novel point prediction predictions radius reliability test training