Every reference with a DOI in the deposited reference list resolved to a known
work in Crossref or DataCite at the dated check, and none carried a retraction,
withdrawal, or removal notice.
The 45 references without a DOI — listed, not checked
no DOI — not checkedThe many faces of robustness: A critical analysis of out-of-distribution generalization
no DOI — not checkedref3
no DOI — not checkedref4
no DOI — not checkedref5
no DOI — not checkedA winning hand: Compressing deep networks can improve out-of-distribution robustness
no DOI — not checkedArtificial neural networks: An overview
no DOI — not checkedQuantifying dnn model robustness to the realworld threats
no DOI — not checkedref9
no DOI — not checkedLearning to validate the predictions of black box classifiers on unseen data
no DOI — not checkedAre labels always necessary for classifier accuracy evaluation?
no DOI — not checkedFailing loudly: An empirical study of methods for detecting dataset shift
no DOI — not checkedAugur: A step towards realistic drift detection in production ml systems
no DOI — not checkedref16
no DOI — not checkedref20
no DOI — not checked3d common corruptions and data augmentation
no DOI — not checkedMeasuring discrimination to boost comparative testing for multiple deep learning models
no DOI — not checkedEnsemble learning: A survey
no DOI — not checkedSelf-checking deep neural networks in deployment
no DOI — not checkedSoftware engineering for machine learning: A case study
no DOI — not checkedComprehensive survey on distance/similarity measures between probability density functions
no DOI — not checkedref29
no DOI — not checkedref30
no DOI — not checkedAdversarial examples are not bugs, they are features
no DOI — not checkedRobust design of deep neural networks against adversarial attacks based on lyapunov theory
no DOI — not checkedref33
no DOI — not checkedref34
no DOI — not checkedref35
no DOI — not checkedref36
no DOI — not checkedBetter diffusion models further improve adversarial training
no DOI — not checkedref38
no DOI — not checkedPrime: A few primitives can boost robustness to common corruptions
no DOI — not checkedref40
no DOI — not checkedref41
no DOI — not checkedref42
no DOI — not checkedref43
no DOI — not checkedAdversarial robustness: From self-supervised pre-training to fine-tuning
no DOI — not checkedQuality metrics in recommender systems: Do we calculate metrics consistently?
no DOI — not checkedref46
no DOI — not checkedUnlabeled data improves adversarial robustness
no DOI — not checkedref49
no DOI — not checkedref50
no DOI — not checkedref51
no DOI — not checkedExploring neural networks with activation atlases
no DOI — not checkedref53
no DOI — not checkedref54
checked 2026-08-28 — re-checked daily as this page is visited;
titles and statuses come from Crossref and DataCite and are not part of the signed record
Both snippets point at the live badge image and link back to this page. The
badge re-renders from the daily check, so an embed never goes stale by more than a day of visits.