arXiv:2601. 02193v2 Announce Type: replace Abstract: We study the extent to which standard machine learning algorithms rely on exchangeability and independence of data by introducing a monotone adversarial corruption model.
arXiv:2607. 03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable.
arXiv:2506. 06891v3 Announce Type: replace Abstract: We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al.
arXiv:2606. 11319v1 Announce Type: new Abstract: Learning from imperfect data is a central theme in machine learning, connecting practical questions of robustness to fundamental questions of learnability.
Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in vision data that can behave like backdoor-like triggers without being maliciously inserted.
arXiv:2406. 05670v3 Announce Type: replace Abstract: Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks.
arXiv:2607. 05516v2 Announce Type: replace-cross Abstract: Model-specific adversarial attacks have been extensively studied.
arXiv:2506. 18020v3 Announce Type: replace Abstract: Robust distributed learning algorithms aim to maintain reliable performance despite the presence of misbehaving workers.
arXiv:2608. 13514v1 Announce Type: cross Abstract: We revisit the problem of learning predictors robust to adversarial examples at test-time.
arXiv:2607. 05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied.
arXiv:2607. 04145v1 Announce Type: new Abstract: Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models.
arXiv:2607. 05898v1 Announce Type: new Abstract: Evaluating whether unlearning algorithms truly remove training data influence remains an open challenge.
We revisit the problem of learning predictors robust to adversarial examples at test-time. We prove that VC classes are adversarially robustly learnable with sample complexity linear in the VC dimension $d$, providing an exponential improvement over the previous upper bound of Montasser, Hanneke, and Srebro (2019).