Robust Models are less Over-Confident

Authors: Julia Grabinski, Paul Gavrikov, Janis Keuper, Margret Keuper

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this paper, we empirically analyze a variety of adversarially trained models that achieve high robust accuracies when facing state-of-the-art attacks and we show that AT has an interesting side-effect: it leads to models that are significantly less overconfident with their decisions, even on clean data than non-robust models. Our experiments for 71 robust and non-robust model pairs on the datasets CIFAR10 [43], CIFAR100 and Image Net [19] confirm that non-robust models are overconfident with their false predictions.
Researcher Affiliation Academia Julia Grabinski Fraunhofer ITWM, Kaiserslautern Visual Computing, University of Siegen julia.grabinski@itwm.fraunhofer.de Paul Gavrikov IMLA, Offenburg University Janis Keuper Fraunhofer ITWM, Kaiserslautern IMLA, Offenburg University Margret Keuper University of Siegen Max Planck Institute for Informatics Saarland Informatics Campus Saarbrücken
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Data & Project website: https://github.com/Ge Julia/robustness_ confidences_evaluation
Open Datasets Yes Our experiments for 71 robust and non-robust model pairs on the datasets CIFAR10 [43], CIFAR100 and Image Net [19] confirm that non-robust models are overconfident with their false predictions.
Dataset Splits Yes CIFAR10 [43] is a simple ten class dataset consisting of 50,000 training and 10,000 validation images with a resolution of 32 32.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments.
Software Dependencies No The paper does not provide specific details about software dependencies, including version numbers for libraries or frameworks used.
Experiment Setup Yes Training details can be found in appendix A.