3 accepted papers
We develop a linear response framework for interpretability that treats a neural network as a Bayesian statistical mechanical system. A small perturbation of the data distribution, for example shifting the Pile toward GitHub or legal text, induces a first-order change in the posterior expectation of…
In many real-world settings exact perturbation sets to be used by an adversary are not plausibly available to a learner. While prior literature has studied both scenarios with completely known and completely unknown perturbation sets, we propose an in-between setting of learning with respect to a cl…
We formally study the problem of classification under adversarial perturbations from a learner’s perspective as well as a third-party who aims at certifying the robustness of a given black-box classifier. We analyze a PAC-type framework of semi-supervised learning and identify possibility and imposs…