We define the robustness measure for the predicted structure of a protein sequence to be the inverse of the root-mean-square distance (RMSD) in the predicted structure and the structure of its adversarially perturbed sequence.
Currently, our ability to build standardized deep learning models is limited by the availability of a suite of neural network and corresponding training hyperparameter benchmarks that expose differences between existing deep learning frameworks.
We exploit this connection and the theory of stochastic dynamical systems to construct a novel ensemble of Itô processes as a new deep learning representation that is more robust than classical residual networks.
We present a new extension of Fano's inequality and employ it to theoretically establish that the probability of success for a membership inference attack on a deep neural network can be bounded using the mutual information between its inputs and its activations.
We demonstrate how a target model's generalization gap leads directly to an effective deterministic black box membership inference attack (MIA).
We study the robustness of machine learning models on benign and adversarial inputs in this neighborhood.