The Many Faces of Adversarial Risk

Authors: Muni Sreenivas Pydi, Varun Jog

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our technical tools derive from optimal transport, robust statistics, functional analysis, and game theory. Our contributions include the following: generalizing Strassen s theorem to the unbalanced optimal transport setting with applications to adversarial classification with unequal priors; showing an equivalence between adversarial robustness and robust hypothesis testing with -Wasserstein uncertainty sets; proving the existence of a pure Nash equilibrium in the two-player game between the adversary and the algorithm; and characterizing adversarial risk by the minimum Bayes error between a pair of distributions belonging to the -Wasserstein uncertainty sets. Our results generalize and deepen recently discovered connections between optimal transport and adversarial robustness and reveal new connections to Choquet capacities and game theory.
Researcher Affiliation Academia Muni Sreenivas Pydi University of Wisconsin Madison Madison, Wisconsin, USA pydi@wisc.edu Varun Jog University of Cambridge Cambridge, UK vj270@cam.ac.uk
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any statement about making its source code publicly available or a link to a code repository.
Open Datasets No The paper is theoretical and does not involve empirical training or evaluation on datasets. It focuses on mathematical definitions and proofs related to adversarial risk and optimal transport.
Dataset Splits No The paper is theoretical and does not involve empirical data splits for validation or training. It discusses mathematical concepts of distributions (p0, p1) but not actual datasets.
Hardware Specification No The paper is theoretical and does not mention any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details such as hyperparameters or training configurations.